© 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. 13528
    Prev
    Next
    INDEX
    Explanations

    Citations in brackets

    np_max-act · gemini-2.0-flash

    The neuron activates on in-text scholarly citation markers (e.g. “[ @… ]” and bracketed reference identifiers).

    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
    _CNT
    -0.08
    subtract
    -0.07
     Manning
    -0.06
     rebound
    -0.06
     мину
    -0.06
     COM
    -0.06
     wisely
    -0.06
     type
    -0.06
     subs
    -0.06
    _merge
    -0.06
    POSITIVE LOGITS
    書館
    0.07
     spriteBatch
    0.06
     досяг
    0.06
    ccak
    0.06
     TOOL
    0.06
     swear
    0.06
    ัฐบาล
    0.06
     AW
    0.06
     thức
    0.06
     immune
    0.06
    Activations Density 0.013%

    No Known Activations