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. 81448
    Prev
    Next
    INDEX
    Explanations

    .length

    np_max-act · gemini-2.0-flash

    This neuron is effectively never triggered—i.e. it does not respond to any tokens.

    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
     pride
    -0.06
     Stories
    -0.06
     lidí
    -0.06
    iate
    -0.06
     Rupert
    -0.06
     setTitle
    -0.06
    hook
    -0.06
     naší
    -0.06
     сучас
    -0.06
    for
    -0.06
    POSITIVE LOGITS
     beh
    0.06
     Chicken
    0.06
    .exc
    0.06
     g
    0.06
    -negative
    0.06
     Rough
    0.06
     ham
    0.06
    .inf
    0.06
     fat
    0.06
    -inf
    0.06
    Activations Density 0.012%

    No Known Activations