© 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. 129817
    Prev
    Next
    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash

    This neuron detects the ordinal‐term pattern in sequence questions—specifically the “’t” token in “n’th term” (e.g. “nth term” queries).

    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
    ią
    -0.07
    _approx
    -0.07
    alloc
    -0.07
    ILA
    -0.07
    ivism
    -0.06
    vise
    -0.06
    _PAR
    -0.06
     ambiguous
    -0.06
    VAR
    -0.06
     bona
    -0.06
    POSITIVE LOGITS
     onder
    0.07
     armed
    0.06
    ำ
    0.06
    umberland
    0.06
    .CLIENT
    0.06
     flute
    0.06
     قانون
    0.06
     WINAPI
    0.06
     وات
    0.06
     warto
    0.06
    Activations Density 0.002%

    No Known Activations