© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110342
    Prev
    Next
    INDEX
    Explanations

    -generated

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of user‐generated content actions and terms (e.g. upload, share, user-generated content).

    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
    GROUND
    -0.07
    round
    -0.07
    vp
    -0.06
     deployment
    -0.06
    .char
    -0.06
    (number
    -0.06
    ROUND
    -0.06
     RuntimeError
    -0.06
    ��
    -0.06
     oak
    -0.06
    POSITIVE LOGITS
     funcion
    0.07
    rescia
    0.07
    (times
    0.07
    -directed
    0.06
    redux
    0.06
     apar
    0.06
    ентом
    0.06
    나요
    0.06
    =pos
    0.06
     Gover
    0.06
    Activations Density 0.032%

    No Known Activations