© 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. 79412
    Prev
    Next
    INDEX
    Explanations

    you

    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
     Leaf
    -0.07
     leaf
    -0.07
    Dr
    -0.07
    -за
    -0.06
    xDE
    -0.06
     Russ
    -0.06
     Then
    -0.06
    ,col
    -0.06
    ỗ
    -0.06
    poi
    -0.06
    POSITIVE LOGITS
     downtown
    0.07
     accommodation
    0.07
    buttonShape
    0.06
    	scene
    0.06
    سنگ
    0.06
    dynamic
    0.06
    _custom
    0.06
    συ
    0.06
     داستان
    0.06
    {'
    0.06
    Activations Density 0.000%

    No Known Activations