© 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. 27607
    Prev
    Next
    INDEX
    Explanations

    contractions

    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
     inflicted
    -0.07
    710
    -0.07
     Conveyor
    -0.07
    rozen
    -0.07
     "../
    -0.06
     prescribe
    -0.06
     пес
    -0.06
     ')';↵
    -0.06
    ा।
    -0.06
    ...↵↵
    -0.06
    POSITIVE LOGITS
     люб
    0.07
    .*
    0.07
    rolley
    0.07
    .async
    0.06
    cliente
    0.06
    celona
    0.06
     bribery
    0.06
    braska
    0.06
     erot
    0.06
    utr
    0.06
    Activations Density 0.120%

    No Known Activations