© 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. 15-RESID-POST-AA
    11. 15554
    Prev
    Next
    INDEX
    Explanations

    two

    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
     zároveň
    -0.08
    )".
    -0.07
    _extent
    -0.07
    ailer
    -0.07
     XIII
    -0.07
     tile
    -0.07
     ik
    -0.07
    $num
    -0.07
    bcm
    -0.07
    ONY
    -0.06
    POSITIVE LOGITS
     guerr
    0.07
     بهتر
    0.07
    _eps
    0.06
     ولم
    0.06
    buttonShape
    0.06
    _begin
    0.06
     peek
    0.06
     pled
    0.06
    crud
    0.05
     Pradesh
    0.05
    Activations Density 0.015%

    No Known Activations