© 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. 3-RESID-POST-AA
    11. 95387
    Prev
    Next
    INDEX
    Explanations

    other languages

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    commended
    -0.06
     سید
    -0.06
     CI
    -0.06
    /gcc
    -0.06
     streaming
    -0.06
     OK
    -0.06
     Observation
    -0.06
     alliance
    -0.06
     Legacy
    -0.06
    .product
    -0.06
    POSITIVE LOGITS
    ้องพ
    0.07
    .emp
    0.07
    半
    0.06
     Wander
    0.06
    .blue
    0.06
    INTERNAL
    0.06
     外部リンク
    0.06
    身体
    0.06
    	RTLR
    0.06
    ぁ
    0.06
    Activations Density 0.007%

    No Known Activations