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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 92724
    Prev
    Next
    INDEX
    Explanations

    goal

    np_max-act · gemini-2.0-flash

    This neuron fires on explicit statements of objectives, specifically on the word “goal” (as in “The goal …”).

    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
    timeofday
    -0.07
    Parsed
    -0.07
    north
    -0.06
    Director
    -0.06
    StringLength
    -0.06
     Joyce
    -0.06
    .GetHashCode
    -0.06
     wget
    -0.06
    arParams
    -0.06
    .putString
    -0.06
    POSITIVE LOGITS
    عي
    0.07
    son
    0.07
     swath
    0.07
     assumption
    0.07
     mohlo
    0.07
     im
    0.07
     verb
    0.06
     hub
    0.06
    etheless
    0.06
     maar
    0.06
    Activations Density 0.054%

    No Known Activations