© 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. 55551
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash

    The neuron responds to question‐forming tokens (like “do,” “pad,” and “?”), i.e. it detects when a question is being asked.

    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
    ivan
    -0.06
    ]['
    -0.06
     treffen
    -0.06
    ulan
    -0.06
    荐
    -0.06
     Safe
    -0.06
    ]["
    -0.06
     advisers
    -0.06
    legg
    -0.06
    сон
    -0.06
    POSITIVE LOGITS
     Verfügung
    0.09
    (!_
    0.07
     miles
    0.07
    ۲۰۱
    0.07
     zvíř
    0.07
    _INFINITY
    0.07
    、な
    0.06
    -К
    0.06
     Sous
    0.06
     confisc
    0.06
    Activations Density 0.057%

    No Known Activations