© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 120967
    Prev
    Next
    INDEX
    Explanations

    parenthesis

    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
     съ
    -0.07
    _tracks
    -0.06
     광
    -0.06
     conexao
    -0.06
     değerlendir
    -0.06
    Entities
    -0.06
    .mp
    -0.06
     snowy
    -0.06
     restroom
    -0.06
     marrying
    -0.06
    POSITIVE LOGITS
    crc
    0.07
    \-
    0.07
    iej
    0.06
    _samples
    0.06
    }.↵
    0.06
    _read
    0.06
     seems
    0.06
    $headers
    0.06
     Determines
    0.06
     resentment
    0.06
    Activations Density 0.001%

    No Known Activations