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. 86307
    Prev
    Next
    INDEX
    Explanations

    * and a letter

    np_max-act · gemini-2.0-flash

    The neuron is specially detecting algebraic terms of the form “coefficient * single-letter variable ** exponent” (i.e. polynomial or power‐expression terms).

    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
    ▏▏
    -0.08
    kı
    -0.07
    际
    -0.06
     IQueryable
    -0.06
    模式
    -0.06
    ят
    -0.06
     innate
    -0.06
     jsonify
    -0.06
    Thai
    -0.06
     MUT
    -0.06
    POSITIVE LOGITS
    َج
    0.07
    quires
    0.06
    /trunk
    0.06
    	LL
    0.06
    .setDescription
    0.06
     Nikola
    0.06
    (J
    0.06
    _VIRTUAL
    0.06
    (Size
    0.06
    Nh
    0.06
    Activations Density 0.004%

    No Known Activations