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. 125153
    Prev
    Next
    INDEX
    Explanations

    Cir

    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
    ocaust
    -0.06
    郭
    -0.06
    意识
    -0.06
    .station
    -0.06
     찬
    -0.06
    农业
    -0.06
     очевид
    -0.06
     threaten
    -0.06
    เรา
    -0.06
    /install
    -0.06
    POSITIVE LOGITS
    (group
    0.08
     roman
    0.07
     pří
    0.06
     cigaret
    0.06
     Elizabeth
    0.06
    ::::|
    0.06
     natur
    0.06
     {:?}",
    0.06
     기다
    0.06
     حي
    0.06
    Activations Density 0.000%

    No Known Activations