© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 59073
    Prev
    Next
    INDEX
    Explanations

    并

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mush
    -0.07
    Nested
    -0.07
     locationManager
    -0.07
    ngen
    -0.06
    DataMember
    -0.06
    .ident
    -0.06
     Rajasthan
    -0.06
    	dest
    -0.06
    šti
    -0.06
     referencia
    -0.06
    POSITIVE LOGITS
     permanently
    0.07
    应当
    0.06
    (theme
    0.06
     семей
    0.06
     Appears
    0.06
     turn
    0.06
    (QL
    0.06
    Board
    0.06
     BAB
    0.06
     pact
    0.06
    Activations Density 0.020%

    No Known Activations