© 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. 126814
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash

    This neuron activates on the key subject noun in “what” questions (e.g. algorithms, policies, inventions, technologies, functions).

    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
     Frage
    -0.07
    �다
    -0.07
    bomb
    -0.07
    ito
    -0.06
    ResponseStatus
    -0.06
    calculator
    -0.06
    PLIT
    -0.06
    _AFTER
    -0.06
    ITO
    -0.06
     Often
    -0.06
    POSITIVE LOGITS
     darkest
    0.07
    _skip
    0.07
     Hlav
    0.07
     REPRESENT
    0.07
    Conn
    0.07
    (radius
    0.06
     Jenn
    0.06
     Jak
    0.06
     BN
    0.06
     parted
    0.06
    Activations Density 0.030%

    No Known Activations