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. 26834
    Prev
    Next
    INDEX
    Explanations

    picking up where left off

    np_max-act · gemini-2.0-flash

    This neuron detects user prompts asking the assistant to continue or resume from where it left off.

    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
     Fusion
    -0.06
    igos
    -0.06
    signals
    -0.06
    已
    -0.06
     grandson
    -0.06
     still
    -0.06
     Airport
    -0.06
     astr
    -0.06
     Rafael
    -0.06
    たい
    -0.06
    POSITIVE LOGITS
    sizei
    0.07
     IKE
    0.06
    .EditorButton
    0.06
    ưa
    0.06
    Frozen
    0.06
    �回
    0.06
     difference
    0.06
     тон
    0.06
    _MS
    0.06
     평
    0.06
    Activations Density 0.008%

    No Known Activations