© 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. 6077
    Prev
    Next
    INDEX
    Explanations

    Code and mixed languages

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on non‐noun tokens (pronouns, verbs, adjectives, prepositions, articles, etc.) and remaining silent on nouns.

    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
    퍼
    -0.07
    �
    -0.06
     }).
    -0.06
     credentials
    -0.06
    _invite
    -0.06
     calloc
    -0.06
    undles
    -0.06
    /detail
    -0.05
     inaccurate
    -0.05
    	short
    -0.05
    POSITIVE LOGITS
     Mash
    0.07
     Bamboo
    0.07
    احی
    0.07
    .nn
    0.07
    abela
    0.07
    รายการ
    0.07
    ولی
    0.06
     vacation
    0.06
     çeşit
    0.06
     getColumn
    0.06
    Activations Density 0.061%

    No Known Activations