Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 88712
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on angle‐bracket template markers (e.g. “<%=” and related “<” tokens in code).

    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
    Publish
    -0.07
    났다
    -0.07
    求购
    -0.06
    .tmp
    -0.06
    -assets
    -0.06
    Cette
    -0.06
    shortcut
    -0.06
     AttributeError
    -0.06
    gm
    -0.06
    .navigate
    -0.06
    POSITIVE LOGITS
    ující
    0.07
    )._
    0.07
    dsn
    0.06
    )[:
    0.06
    Allen
    0.06
    }>
    ↵
    0.06
     indexed
    0.06
     =>$
    0.06
     els
    0.06
    าหาร
    0.06
    Activations Density 0.052%

    No Known Activations