© 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. 8766
    Prev
    Next
    INDEX
    Explanations

    Enhancement

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of combining game elements—particularly card combination or “combine” actions and their numerical or effect results.

    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
     StatusCode
    -0.07
     brace
    -0.07
     towers
    -0.07
     Raiders
    -0.06
    reatment
    -0.06
    (valor
    -0.06
    違
    -0.06
     هدف
    -0.06
    ="$
    -0.06
     Jackets
    -0.06
    POSITIVE LOGITS
    _rem
    0.07
     zinc
    0.07
     Codec
    0.07
    .getId
    0.06
    chip
    0.06
    ayın
    0.06
    ála
    0.06
     dec
    0.06
     नई
    0.06
     істор
    0.06
    Activations Density 0.026%

    No Known Activations