© 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. 109703
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of chemical or biological substances (e.g., hormones, ions, bacteria) being described as “present in” a medium or environment.

    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
     name
    -0.07
    出去
    -0.07
    879
    -0.06
    ANGUAGE
    -0.06
    wagon
    -0.06
    مو
    -0.06
     genocide
    -0.06
    586
    -0.06
    	tmp
    -0.06
    ,bool
    -0.06
    POSITIVE LOGITS
     rain
    0.06
    climate
    0.06
    \core
    0.06
     pozit
    0.06
     dispos
    0.06
     Pleasant
    0.06
    (button
    0.06
     coinc
    0.06
    izzling
    0.06
    (axis
    0.06
    Activations Density 0.034%

    No Known Activations