© 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. 73613
    Prev
    Next
    INDEX
    Explanations

    excuse

    np_max-act · gemini-2.0-flash

    content related to personal experiences and reflections on service or product disappointments.

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

    This neuron detects occurrences of the word “excuse,” especially in “no excuse” constructions.

    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
    >The
    -0.07
    .JTable
    -0.07
    bond
    -0.07
     tried
    -0.07
     physicists
    -0.07
    Stars
    -0.07
     brought
    -0.06
    Typed
    -0.06
     letto
    -0.06
     vale
    -0.06
    POSITIVE LOGITS
    HQ
    0.08
    班
    0.06
    getOrElse
    0.06
     RECEIVER
    0.06
    胜
    0.06
    parentId
    0.06
    шев
    0.06
    enstein
    0.06
     квад
    0.06
     올
    0.06
    Activations Density 0.005%

    No Known Activations