© 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. 73213
    Prev
    Next
    INDEX
    Explanations

    code and configurations

    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
    ="$(
    -0.07
     scaleX
    -0.07
     oxide
    -0.06
     @"
    -0.06
    (handler
    -0.06
    shipment
    -0.06
    نامج
    -0.06
    StateChanged
    -0.06
     Как
    -0.06
    	tile
    -0.06
    POSITIVE LOGITS
    edm
    0.07
    _visual
    0.07
     betr
    0.07
    der
    0.07
    _Bl
    0.06
    chn
    0.06
    bers
    0.06
     �
    0.06
    ulling
    0.06
    _students
    0.06
    Activations Density 0.310%

    No Known Activations