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. 19-RESID-POST-AA
    6. 31025
    Prev
    Next
    INDEX
    Explanations

    What

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spice
    -0.08
     sales
    -0.06
     biting
    -0.06
     gamb
    -0.06
     numbering
    -0.06
    OMATIC
    -0.06
     USB
    -0.06
     Deze
    -0.06
     код
    -0.06
     thickness
    -0.06
    POSITIVE LOGITS
     ************************
    0.07
    .unsqueeze
    0.07
     تلك
    0.07
     persecuted
    0.06
     výrob
    0.06
     مقاله
    0.06
    lut
    0.06
    اره
    0.06
    -Mail
    0.06
    (atom
    0.06
    Activations Density 0.009%

    No Known Activations