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. 23-RESID-POST-AA
    6. 40623
    Prev
    Next
    INDEX
    Explanations

    Roberto

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _chunk
    -0.06
     satisfying
    -0.06
    maze
    -0.06
    ecektir
    -0.06
     Education
    -0.06
    /stream
    -0.06
    messages
    -0.06
    .layers
    -0.06
     assigns
    -0.06
    _boundary
    -0.05
    POSITIVE LOGITS
    нув
    0.09
    .REACT
    0.08
     tém
    0.07
     defaultProps
    0.07
    (any
    0.07
     corrobor
    0.07
     мет
    0.07
     MyApp
    0.07
    DOWNLOAD
    0.07
     DEAL
    0.06
    Activations Density 0.001%

    No Known Activations