Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 111660
    Prev
    Next
    INDEX
    Explanations

    word

    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
     Hud
    -0.07
     concurrent
    -0.07
    sie
    -0.06
    _COST
    -0.06
    :F
    -0.06
    (host
    -0.06
     urged
    -0.06
     PI
    -0.06
    _VOL
    -0.06
     Puppet
    -0.06
    POSITIVE LOGITS
    bohydr
    0.07
    ************************
    0.07
    ysize
    0.07
    typeparam
    0.07
     Cent
    0.06
     initWithStyle
    0.06
     onBindViewHolder
    0.06
     bý
    0.06
    であった
    0.06
     mortgage
    0.06
    Activations Density 0.028%

    No Known Activations