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. 99432
    Prev
    Next
    INDEX
    Explanations

    reduce

    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
     getAll
    -0.07
    .setItem
    -0.07
     xm
    -0.06
     absor
    -0.06
     etmiş
    -0.06
     dual
    -0.06
    ิท
    -0.06
     proport
    -0.06
    Knight
    -0.06
     Increment
    -0.06
    POSITIVE LOGITS
    reduce
    0.11
    adoop
    0.09
    .hadoop
    0.08
    Reduce
    0.07
     litt
    0.07
    oop
    0.07
    �
    0.06
    ジェ
    0.06
    sil
    0.06
    凉
    0.06
    Activations Density 0.001%

    No Known Activations