© 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. 43276
    Prev
    Next
    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash

    statements regarding technology-related misunderstandings or criticisms.

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

    This neuron detects interrogative phrasing—i.e. question words or question-mark 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
    :::::
    -0.07
    (In
    -0.07
     улыб
    -0.07
    rientation
    -0.06
     h�
    -0.06
    (datetime
    -0.06
     ------------------------------------------------------------------------------------------------
    -0.06
    _tooltip
    -0.06
    ToAdd
    -0.06
     strife
    -0.06
    POSITIVE LOGITS
     COL
    0.07
     AppModule
    0.07
     coi
    0.06
     Feder
    0.06
     Ferr
    0.06
     James
    0.06
     survivor
    0.06
    -core
    0.06
     projected
    0.06
     Klan
    0.06
    Activations Density 0.016%

    No Known Activations