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. 39430
    Prev
    Next
    INDEX
    Explanations

    State

    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
    .constraint
    -0.08
     BlockPos
    -0.06
    яс
    -0.06
    ongyang
    -0.06
    .F
    -0.06
    ón
    -0.05
    _instruction
    -0.05
    patibility
    -0.05
    c
    -0.05
     Occupational
    -0.05
    POSITIVE LOGITS
     Ramsey
    0.07
     Bond
    0.07
     sentence
    0.07
     dissolve
    0.07
     कव
    0.07
    =e
    0.07
    -site
    0.06
     Heritage
    0.06
     Slice
    0.06
     vinegar
    0.06
    Activations Density 0.001%

    No Known Activations