© 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. 15-RESID-POST-AA
    11. 19744
    Prev
    Next
    INDEX
    Explanations

    Unstructured text

    np_max-act · gemini-2.0-flash

    common short function words (auxiliaries/pronouns/simple verbs) that occur within sentences.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OB
    -0.07
    เจ
    -0.06
     Nodes
    -0.06
    raph
    -0.06
    альное
    -0.06
    шем
    -0.06
    her
    -0.06
     газ
    -0.06
     autistic
    -0.06
    들도
    -0.06
    POSITIVE LOGITS
    (features
    0.07
    .contents
    0.07
    	points
    0.07
    "][
    0.06
    	category
    0.06
    melon
    0.06
    	double
    0.06
    (parts
    0.06
    ayas
    0.06
     خدم
    0.06
    Activations Density 0.000%

    No Known Activations