© 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. 585
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “next time” (i.e. future‐reference tokens like “next” and “time”).

    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
    _walk
    -0.08
    라고
    -0.07
     thirteen
    -0.07
     nos
    -0.07
     unusual
    -0.06
     있도록
    -0.06
     bulletin
    -0.06
     Intermediate
    -0.06
     Doe
    -0.06
     Bölüm
    -0.06
    POSITIVE LOGITS
     time
    0.10
     everytime
    0.08
    ство
    0.07
    во
    0.06
    icate
    0.06
     손
    0.06
    Trou
    0.06
     einz
    0.06
     chac
    0.06
     Time
    0.06
    Activations Density 0.017%

    No Known Activations