© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 24773
    Prev
    Next
    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash

    requests or imperatives that ask the assistant to analyze, observe, speculate, or explain something.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    Phrases and tokens that signal a user's instruction or request (imperative prompts like "look at," "speculate," and similar command-style openings in the user header).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liament
    -0.07
    punk
    -0.07
     Každ
    -0.06
    ]){
↵
    -0.06
     swallowed
    -0.06
     Lambda
    -0.06
    _dispatcher
    -0.06
     کردند
    -0.06
    .Do
    -0.06
    .compareTo
    -0.06
    POSITIVE LOGITS
     CFG
    0.07
    (workspace
    0.07
     PIL
    0.06
    _IB
    0.06
     Grimm
    0.06
     plethora
    0.06
    need
    0.06
     буду
    0.06
    İTESİ
    0.06
    inium
    0.06
    Activations Density 1.414%

    No Known Activations