© 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. 112236
    Prev
    Next
    INDEX
    Explanations

    Saving files

    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
    ิกา
    -0.07
    rank
    -0.06
    -gl
    -0.06
    JOIN
    -0.06
     showcases
    -0.06
    aining
    -0.06
    eps
    -0.06
    coins
    -0.06
     часов
    -0.06
    ials
    -0.06
    POSITIVE LOGITS
     σχ
    0.08
     impose
    0.06
    ุญาต
    0.06
     temperament
    0.06
     licking
    0.06
     sứ
    0.06
    (tmp
    0.06
     Designed
    0.06
     generally
    0.06
    権
    0.06
    Activations Density 0.047%

    No Known Activations