© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 49810
    Prev
    Next
    INDEX
    Explanations

    third

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the third item in a sequence, i.e. the ordinal “third” marking a third occurrence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    legal terms and references related to court proceedings.

    oai_token-act-pair · gpt-4o-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
    日期
    -0.06
    isEqual
    -0.06
    ijd
    -0.06
     Dropout
    -0.06
     ई
    -0.06
    .rl
    -0.06
    ینگ
    -0.06
     noh
    -0.06
     kuv
    -0.05
     reactors
    -0.05
    POSITIVE LOGITS
    $rows
    0.07
     Elo
    0.07
    _REALTYPE
    0.07
     moduleId
    0.07
     نسبت
    0.06
    -pagination
    0.06
    cerpt
    0.06
     Matchers
    0.06
    licht
    0.06
    atego
    0.06
    Activations Density 0.156%

    No Known Activations