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. 125133
    Prev
    Next
    INDEX
    Explanations

    Expatriate sportspeople categories

    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
    rowned
    -0.07
    ria
    -0.07
    添加
    -0.06
    Enabled
    -0.06
    _MALLOC
    -0.06
    -men
    -0.06
    ips
    -0.06
    _intf
    -0.06
    .sa
    -0.06
    :relative
    -0.06
    POSITIVE LOGITS
    पर
    0.06
     climate
    0.06
     displaced
    0.06
    ictor
    0.06
    IMAGE
    0.06
    CASE
    0.06
    _FLOAT
    0.06
     AB
    0.06
     структу
    0.06
     POP
    0.06
    Activations Density 0.002%

    No Known Activations