© 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. 91687
    Prev
    Next
    INDEX
    Explanations

    remember

    np_max-act · gemini-2.0-flash

    This neuron fires on hedging phrases expressing uncertainty or inability to recall (e.g. “I can’t remember off the top of my head,” “I can’t recall off hand,” etc.).

    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
    allax
    -0.08
    زه
    -0.07
     boycott
    -0.07
     môi
    -0.06
    gorithm
    -0.06
    چه
    -0.06
     sour
    -0.06
     середови
    -0.06
    CHE
    -0.06
    _Search
    -0.06
    POSITIVE LOGITS
     ….
    0.07
    ?"↵↵
    0.06
    功
    0.06
    ":{"
    0.06
    到了
    0.06
    ime
    0.06
     comedic
    0.06
    ือง
    0.06
    Getty
    0.06
     Bj
    0.06
    Activations Density 0.012%

    No Known Activations