© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 19542
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    boilerplate assistant-safe/respectful preface phrases (e.g., "As a helpful and respectful assistant, I’m happy to…").

    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
     readOnly
    -0.06
    smtp
    -0.06
    '},
    -0.06
    hidden
    -0.06
     rval
    -0.06
     tts
    -0.06
     Antar
    -0.06
     ctr
    -0.06
    غر
    -0.05
    Wildcard
    -0.05
    POSITIVE LOGITS
    /src
    0.07
    amientos
    0.07
    >>↵
    0.07
     уклад
    0.07
    砲
    0.07
    億
    0.06
    -fix
    0.06
    covered
    0.06
    ====↵
    0.06
     Anatomy
    0.06
    Activations Density 0.010%

    No Known Activations