© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128391
    Prev
    Next
    INDEX
    Explanations

    values and differences

    np_max-act · gemini-2.0-flash

    sentences that describe the location and purpose of objects or entities in a given context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the “Answer” label (and its accompanying colon) when formatting question‐and‐answer text.

    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
    цес
    -0.07
     Aleppo
    -0.06
     curl
    -0.06
     Sentry
    -0.06
     chunks
    -0.06
    tica
    -0.06
    chunks
    -0.06
     tcb
    -0.06
     DACA
    -0.06
    annotations
    -0.06
    POSITIVE LOGITS
     denom
    0.07
    -delay
    0.07
     ngược
    0.07
    .Execute
    0.07
    レ
    0.07
    XMLLoader
    0.06
     ґ
    0.06
     Quantity
    0.06
    _assign
    0.06
    (LayoutInflater
    0.06
    Activations Density 0.021%

    No Known Activations