© 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. 126656
    Prev
    Next
    INDEX
    Explanations

    status

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “status,” especially when used as a heading or label (e.g. “Status”).

    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
     vine
    -0.08
     quote
    -0.07
     twelve
    -0.07
    ween
    -0.07
    /main
    -0.07
    aket
    -0.07
    210
    -0.06
     Mine
    -0.06
     Remote
    -0.06
     Let
    -0.06
    POSITIVE LOGITS
     status
    0.15
    Status
    0.13
     Status
    0.12
    status
    0.11
     statuses
    0.10
    -status
    0.09
    	status
    0.09
    _status
    0.09
    estatus
    0.09
    _Status
    0.08
    Activations Density 0.018%

    No Known Activations