© 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. 4940
    Prev
    Next
    INDEX
    Explanations

    ----------------------------

    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
     shaping
    -0.08
     bounced
    -0.07
     Sandwich
    -0.07
     staying
    -0.06
     scheduled
    -0.06
     Char
    -0.06
     spl
    -0.06
    holders
    -0.06
     peach
    -0.06
     transc
    -0.06
    POSITIVE LOGITS
     GUIDE
    0.07
     Ji
    0.07
     vůči
    0.07
    ایج
    0.06
    }`}
    0.06
     değiştir
    0.06
     mağ
    0.06
     ij
    0.06
    повід
    0.06
     Diagnosis
    0.06
    Activations Density 0.003%

    No Known Activations