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. 86040
    Prev
    Next
    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash

    The neuron detects common sentence-initial words (like “There,” “Here,” “It,” “The,” etc.) that introduce explanatory or descriptive statements.

    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
     دش
    -0.07
    ниця
    -0.06
    ahoma
    -0.06
    Sher
    -0.06
     glacier
    -0.06
    aepernick
    -0.06
    \Plugin
    -0.06
     sich
    -0.06
    ExceptionHandler
    -0.06
    /epl
    -0.06
    POSITIVE LOGITS
     thereof
    0.07
    numberOf
    0.07
     мож
    0.07
    ことで
    0.07
     Playing
    0.06
    licative
    0.06
    γκο
    0.06
    has
    0.06
     продаж
    0.06
    ....
    0.06
    Activations Density 0.067%

    No Known Activations