© 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. 128132
    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
     functions
    -0.07
     control
    -0.07
    masters
    -0.07
    {%
    -0.07
     classifications
    -0.07
    adelphia
    -0.06
    Card
    -0.06
    -id
    -0.06
     cylinder
    -0.06
     wings
    -0.06
    POSITIVE LOGITS
    ernals
    0.06
     ธ
    0.06
    ewear
    0.06
    _LA
    0.06
    	Code
    0.06
     Beaut
    0.06
    _retry
    0.06
    -eslint
    0.06
    ates
    0.06
     tion
    0.05
    Activations Density 0.008%

    No Known Activations