© 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. 89796
    Prev
    Next
    INDEX
    Explanations

    machine learning

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of pretraining the model on large amounts of text data.

    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
     Colombian
    -0.07
    iddles
    -0.07
    _pause
    -0.07
     |=
    -0.06
     instancia
    -0.06
    047
    -0.06
     chẳng
    -0.06
    _ordered
    -0.06
    .IsEmpty
    -0.06
     Население
    -0.06
    POSITIVE LOGITS
     surpr
    0.07
    uff
    0.06
    unting
    0.06
    UFF
    0.06
    shore
    0.06
     �
    0.06
    <|start_header_id|>
    0.06
    \Json
    0.06
     door
    0.06
     judge
    0.06
    Activations Density 0.023%

    No Known Activations