© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42514
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash

    This neuron detects words in the explanation of the “successor representation” for ordinal numbers (i.e. the discussion of replacing ordinal names with numeric prefixes).

    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
     Modi
    -0.07
    974
    -0.07
     scams
    -0.06
     UPDATED
    -0.06
     paed
    -0.06
     الرياض
    -0.06
    IDX
    -0.06
    (cal
    -0.06
     incap
    -0.06
     Focus
    -0.06
    POSITIVE LOGITS
    indice
    0.07
    	cl
    0.07
    콩
    0.07
    .setVertical
    0.06
    essenger
    0.06
     :)↵
    0.06
    ίγ
    0.06
     renderItem
    0.06
    .setMaximum
    0.06
    _Table
    0.06
    Activations Density 0.170%

    No Known Activations