Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 31186
    Prev
    Next
    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    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
    _rg
    -0.07
     chats
    -0.07
    \Factory
    -0.07
    (list
    -0.06
    (place
    -0.06
    .sort
    -0.06
     sapi
    -0.06
    lient
    -0.06
     Era
    -0.06
    	lib
    -0.06
    POSITIVE LOGITS
     ('
    0.07
    RIA
    0.07
     तत
    0.06
    س
    0.06
    Stat
    0.06
    indo
    0.06
    _ComCallableWrapper
    0.06
    eliac
    0.06
     відом
    0.06
     Kıs
    0.06
    Activations Density 0.015%

    No Known Activations