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. 110598
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    otify
    -0.07
    cha
    -0.07
    ंडल
    -0.06
    offline
    -0.06
    (decoded
    -0.06
     precautions
    -0.06
    UTDOWN
    -0.06
    Prov
    -0.06
    ického
    -0.06
     stared
    -0.06
    POSITIVE LOGITS
    .extent
    0.06
    .point
    0.06
    refresh
    0.06
    .UseVisualStyleBackColor
    0.06
     ){↵
    0.06
     banka
    0.06
     ################################################
    0.06
     Personnel
    0.06
    statt
    0.06
    (condition
    0.06
    Activations Density 0.079%

    No Known Activations