© 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. 55573
    Prev
    Next
    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of changes in biological expression or regulation (e.g. “up-regulated,” “down-regulated,” “overexpression”).

    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
    нич
    -0.08
    fraction
    -0.08
     salmon
    -0.07
     americ
    -0.07
    Americ
    -0.07
    “그
    -0.07
     imageName
    -0.06
     fetal
    -0.06
    싱
    -0.06
    Slides
    -0.06
    POSITIVE LOGITS
     ersten
    0.07
     JOptionPane
    0.06
    =====↵
    0.06
     rev
    0.06
    ;-
    0.06
     campaigns
    0.06
    -en
    0.06
     pros
    0.06
     alterations
    0.06
     En
    0.06
    Activations Density 0.006%

    No Known Activations