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. 83546
    Prev
    Next
    INDEX
    Explanations

    Vo

    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
    plement
    -0.06
    iter
    -0.06
    _Cancel
    -0.06
     epub
    -0.06
    Remove
    -0.06
    _refer
    -0.06
     contemplated
    -0.06
     slug
    -0.06
     Stern
    -0.06
    _native
    -0.05
    POSITIVE LOGITS
    .ai
    0.08
    (gs
    0.07
    <TextView
    0.07
     stroj
    0.07
    กร
    0.07
     '",
    0.07
    .setLocation
    0.07
    보
    0.06
    _options
    0.06
    ho
    0.06
    Activations Density 0.006%

    No Known Activations