© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73802
    Prev
    Next
    INDEX
    Explanations

    Spot

    np_max-act · gemini-2.0-flash

    The neuron is looking for occurrences of the word “spot” (including in compounds like “spotlight” or “spot‐scanning”).

    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
    اعدة
    -0.07
    .calculate
    -0.07
     twelve
    -0.07
    ulaire
    -0.07
    .ke
    -0.07
     maintenance
    -0.07
     Merge
    -0.07
    _calc
    -0.07
     balance
    -0.07
     turbine
    -0.07
    POSITIVE LOGITS
     spot
    0.17
     Spot
    0.14
     spots
    0.13
     spotting
    0.12
     spotted
    0.11
    spots
    0.10
    -spot
    0.10
    Spot
    0.10
    spot
    0.09
    pt
    0.08
    Activations Density 0.009%

    No Known Activations