© 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. 12697
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    This neuron detects hedge phrases expressing inference or uncertainty (e.g. “from what I can tell,” “from what I can see”).

    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
     Pharmacy
    -0.07
     Branch
    -0.07
    esinde
    -0.07
     浙江
    -0.06
     synthesis
    -0.06
    UBLIC
    -0.06
    -operator
    -0.06
     Ist
    -0.06
     сентября
    -0.06
    _backend
    -0.06
    POSITIVE LOGITS
     �
    0.07
    인
    0.07
    _ten
    0.07
    ///<
    0.07
    Invite
    0.07
    ([
↵
    0.06
    )){
↵
    0.06
    ruž
    0.06
     了
    0.06
    	spec
    0.06
    Activations Density 0.020%

    No Known Activations