© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29685
    Prev
    Next
    INDEX
    Explanations

    Company market presence

    np_max-act · gemini-2.0-flash

    This neuron spotlights mentions of a company’s “strong presence in” (i.e., references to having a notable market or geographic presence).

    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
    ication
    -0.07
     celery
    -0.07
    .TextField
    -0.07
    (uid
    -0.06
    dev
    -0.06
     ctypes
    -0.06
    .weight
    -0.06
     crisis
    -0.06
     Lives
    -0.06
     openid
    -0.06
    POSITIVE LOGITS
     generics
    0.07
    ethical
    0.07
     davran
    0.06
    ік
    0.06
    oooooooo
    0.06
     enrol
    0.06
     PROVIDED
    0.06
     karış
    0.06
    ับร
    0.06
     몰
    0.06
    Activations Density 0.017%

    No Known Activations