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. 40450
    Prev
    Next
    INDEX
    Explanations

    punctuation in code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric age mentions (e.g. the whiskey’s “10,” “12,” “14,” “16,” or “18 Year Old” 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
    Only
    -0.07
     Levine
    -0.07
    컵
    -0.07
     whole
    -0.07
    Guy
    -0.07
    매
    -0.07
    εύ
    -0.07
    _DOMAIN
    -0.06
     Frankfurt
    -0.06
    )))));↵
    -0.06
    POSITIVE LOGITS
    .Atoi
    0.06
     wander
    0.06
    +self
    0.06
    йте
    0.06
    _mul
    0.06
    essen
    0.05
    CHKERRQ
    0.05
     вклад
    0.05
    (numpy
    0.05
    getOption
    0.05
    Activations Density 0.190%

    No Known Activations