© 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. 126029
    Prev
    Next
    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash

    This neuron detects instruction-language tokens specifying the retrieval of particular pieces of information for each holding (e.g., “Retrieve,” “holding,” “each,” “from”).

    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
    CharCode
    -0.07
     nug
    -0.06
    _MIDDLE
    -0.06
     حرف
    -0.06
    []{"
    -0.06
     парт
    -0.06
    itoris
    -0.06
    (){↵↵
    -0.06
    /↵↵↵
    -0.06
     ocur
    -0.06
    POSITIVE LOGITS
     handled
    0.07
    00
    0.07
    _SAMPL
    0.06
    -loss
    0.06
    255
    0.06
    884
    0.06
     redeemed
    0.06
    65
    0.06
    зация
    0.06
     TOD
    0.06
    Activations Density 0.012%

    No Known Activations