© 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. 85712
    Prev
    Next
    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens and coefficients in mathematical expressions, i.e. it detects numbers in equations.

    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
    _again
    -0.07
    MMC
    -0.07
    Typ
    -0.06
     zoekt
    -0.06
    propertyName
    -0.06
    हर
    -0.06
    _appro
    -0.06
    retval
    -0.06
     кап
    -0.06
    ethod
    -0.06
    POSITIVE LOGITS
    科
    0.06
     Thumb
    0.06
    發
    0.06
    sak
    0.06
    _ONLY
    0.06
     ve
    0.06
     Skin
    0.06
     flu
    0.06
    arena
    0.06
     pontos
    0.06
    Activations Density 0.002%

    No Known Activations