© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92505
    Prev
    Next
    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash

    text related to legal proceedings and court cases.

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

    The neuron activates on occurrences of the word “require” (and its inflected forms), i.e. tokens expressing a mandate or requirement.

    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
    17
    -0.07
     redis
    -0.07
     gloss
    -0.07
    .read
    -0.06
    ENTRY
    -0.06
     developer
    -0.06
     француз
    -0.06
     varying
    -0.06
     Huang
    -0.06
     alcohol
    -0.06
    POSITIVE LOGITS
    -android
    0.07
    .ToInt
    0.07
     Crimea
    0.07
     requiring
    0.07
     buộc
    0.06
    -pagination
    0.06
     demanding
    0.06
    ibbean
    0.06
    required
    0.06
    ogonal
    0.06
    Activations Density 0.016%

    No Known Activations