© 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. 61187
    Prev
    Next
    INDEX
    Explanations

    challenge

    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
    рукт
    -0.06
     PVC
    -0.06
    piar
    -0.06
     переход
    -0.06
     Payment
    -0.06
     kd
    -0.06
     карт
    -0.06
     RK
    -0.06
    /docker
    -0.06
    -paid
    -0.06
    POSITIVE LOGITS
     challenger
    0.10
     Challenger
    0.08
     Comedy
    0.07
     challeng
    0.07
     altogether
    0.07
     Crisis
    0.07
    客
    0.06
    とき
    0.06
     contender
    0.06
     challenging
    0.06
    Activations Density 0.007%

    No Known Activations