© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54362
    Prev
    Next
    INDEX
    Explanations

    Character descriptions

    np_max-act · gemini-2.0-flash

    The neuron responds to descriptive modifiers—particularly attributive adjectives (like “prestigious,” “affluent,” “educated,” etc.) that characterize a named entity.

    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
     tote
    -0.07
    Grammar
    -0.07
    於
    -0.06
    AME
    -0.06
     samp
    -0.06
     ayrıntılı
    -0.06
     ice
    -0.06
     Γι
    -0.06
     fur
    -0.06
    .Surface
    -0.06
    POSITIVE LOGITS
     Trinity
    0.06
     standout
    0.06
    consum
    0.06
     acl
    0.06
     masc
    0.06
    覺
    0.06
     हट
    0.06
    ptrdiff
    0.06
    =view
    0.06
    ebi
    0.06
    Activations Density 0.004%

    No Known Activations