© 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. 126095
    Prev
    Next
    INDEX
    Explanations

    Questions and instructions

    np_max-act · gemini-2.0-flash

    The neuron fires on special structural or control tokens (e.g. header markers, system tags, start/end-of-text delimiters) rather than ordinary words.

    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
     ={
    -0.07
     Languages
    -0.07
    _GATE
    -0.07
    αρ
    -0.06
    >w
    -0.06
     pensions
    -0.06
     =(
    -0.06
     siè
    -0.06
    وند
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    」↵
    0.07
    macen
    0.06
    osaic
    0.06
     ++
    0.06
    ();?>
    0.06
     První
    0.06
    ValueHandling
    0.06
    [now
    0.06
    \Action
    0.06
    Strict
    0.06
    Activations Density 0.004%

    No Known Activations