© 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. 112888
    Prev
    Next
    INDEX
    Explanations

    _ci

    np_max-act · gemini-2.0-flash
    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
    	include
    -0.06
     cauliflower
    -0.06
    "s
    -0.06
    <|begin_of_text|>
    -0.06
    eldig
    -0.06
     twee
    -0.06
    .S
    -0.06
    相手
    -0.06
     choisir
    -0.06
    	headers
    -0.06
    POSITIVE LOGITS
    _ci
    0.08
     Requests
    0.07
    (elem
    0.07
    '});↵
    0.07
     hton
    0.07
     stanza
    0.07
    	Response
    0.07
    ifiable
    0.07
    isti
    0.06
     Ferm
    0.06
    Activations Density 0.001%

    No Known Activations