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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 18706
    Prev
    Next
    INDEX
    Explanations

    to

    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
     вже
    -0.07
    asil
    -0.07
     
    -0.06
    avel
    -0.06
    نج
    -0.06
     CString
    -0.06
    mods
    -0.06
     сос
    -0.06
    ráci
    -0.06
     harmon
    -0.06
    POSITIVE LOGITS
    -pe
    0.07
     elbow
    0.06
     intermediate
    0.06
     contradictory
    0.06
    dropIfExists
    0.06
     tossed
    0.06
    .cuda
    0.06
    ленных
    0.06
    xious
    0.06
    _kind
    0.06
    Activations Density 0.022%

    No Known Activations