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. 16165
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    The neuron never activates (all its activation values remain zero), so it does not detect any pattern in the text.

    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
     MESSAGE
    -0.07
     vault
    -0.07
     starter
    -0.07
     franc
    -0.06
    _One
    -0.06
     stylist
    -0.06
     Appalachian
    -0.06
     tra
    -0.06
    cient
    -0.06
     nombre
    -0.06
    POSITIVE LOGITS
    Such
    0.07
    ylabel
    0.07
     Nullable
    0.06
    �
    0.06
    宋体
    0.06
     Liability
    0.06
    (sprite
    0.06
     окт
    0.06
    ůj
    0.06
    ゆ
    0.06
    Activations Density 0.044%

    No Known Activations