Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 40353
    Prev
    Next
    INDEX
    Explanations

    loss

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     먼저
    -0.07
    cellent
    -0.07
    Wik
    -0.06
    oen
    -0.06
    _DESC
    -0.06
    __).
    -0.06
     saldır
    -0.06
     excellent
    -0.06
    Excellent
    -0.06
     dryer
    -0.06
    POSITIVE LOGITS
    _PIXEL
    0.07
    lost
    0.06
    ABEL
    0.06
    flamm
    0.06
     missing
    0.06
    (^
    0.06
     jl
    0.06
    Ba
    0.06
     �
    0.06
     Given
    0.06
    Activations Density 0.001%

    No Known Activations