© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 42665
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens from the “moody old fart” character bio—i.e. descriptions of a grumpy elderly persona.

    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
     زمینه
    -0.07
    ンク
    -0.06
    κος
    -0.06
    MX
    -0.06
    вих
    -0.06
    elseif
    -0.06
    impse
    -0.06
    語
    -0.06
    因为
    -0.06
    ssize
    -0.06
    POSITIVE LOGITS
    植物
    0.06
     Chris
    0.06
    _Vector
    0.06
     salary
    0.06
     طور
    0.06
     nek
    0.06
    Não
    0.06
    ))).
    0.06
    _DOCUMENT
    0.05
    @g
    0.05
    Activations Density 0.013%

    No Known Activations