© 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. 11-RESID-POST-AA
    11. 104981
    Prev
    Next
    INDEX
    Explanations

    ethyl

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Types
    -0.07
    _second
    -0.06
    ."]
    -0.06
    _both
    -0.06
    _OPER
    -0.06
    spl
    -0.06
     chút
    -0.06
     Fiona
    -0.06
    	P
    -0.06
    _Player
    -0.06
    POSITIVE LOGITS
     observation
    0.08
    Jets
    0.07
     iteration
    0.06
     ас
    0.06
     enquiries
    0.06
    ogh
    0.06
     Malays
    0.06
    谷
    0.06
    exels
    0.06
    CKET
    0.06
    Activations Density 0.012%

    No Known Activations