© 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. 19-RESID-POST-AA
    11. 10866
    Prev
    Next
    INDEX
    Explanations

    relationships/friendships

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wildly
    -0.07
    arpa
    -0.07
    Driving
    -0.07
    ubic
    -0.06
    .DropDownItems
    -0.06
    .Person
    -0.06
     ########################
    -0.06
     SPORT
    -0.06
     Price
    -0.06
    REAK
    -0.06
    POSITIVE LOGITS
    詳細
    0.07
    ερ
    0.06
     يم
    0.06
    .enter
    0.06
    隔
    0.06
    .FC
    0.06
    िग
    0.06
     Fantasy
    0.06
     Dresden
    0.06
     Keys
    0.06
    Activations Density 0.061%

    No Known Activations