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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 16184
    Prev
    Next
    INDEX
    Explanations

    pt

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the token sequence “GPT” (i.e. mentions of the GPT model name).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .GetOrdinal
    -0.06
    KeyCode
    -0.06
    ’an
    -0.06
    -you
    -0.06
    <button
    -0.06
    ayas
    -0.06
    374
    -0.06
    -validator
    -0.06
    ':''
    -0.06
    :result
    -0.06
    POSITIVE LOGITS
     GUID
    0.06
     repar
    0.06
    ersion
    0.06
     autop
    0.06
    追
    0.06
    (Position
    0.06
    recogn
    0.06
    NSUInteger
    0.06
    BTTag
    0.06
    �
    0.06
    Activations Density 0.005%

    No Known Activations