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. 130691
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens containing a decimal point (i.e. floating-point numbers).

    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
     carving
    -0.07
    .group
    -0.06
     Independence
    -0.06
    Driver
    -0.06
     impulse
    -0.06
    狼
    -0.06
    _DOMAIN
    -0.06
     QTableWidgetItem
    -0.06
     invaders
    -0.06
    (list
    -0.06
    POSITIVE LOGITS
    starttime
    0.07
     dying
    0.06
    @RequestParam
    0.06
     아직
    0.06
    (raw
    0.06
     Affiliate
    0.06
    _BACK
    0.06
    nnen
    0.06
    ADMIN
    0.06
     destructor
    0.06
    Activations Density 0.001%

    No Known Activations