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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 80776
    Prev
    Next
    INDEX
    Explanations

    for

    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
    거나
    -0.06
     IUser
    -0.06
    すれば
    -0.06
     Merkezi
    -0.06
    必要
    -0.06
     Eh
    -0.06
     winners
    -0.06
     уник
    -0.06
     Guill
    -0.06
     Benny
    -0.06
    POSITIVE LOGITS
    .onOptionsItemSelected
    0.07
    _escape
    0.06
    _AGENT
    0.06
    /router
    0.06
    	stat
    0.06
    .star
    0.06
     architects
    0.06
     setResult
    0.06
     getState
    0.06
    оля
    0.06
    Activations Density 0.272%

    No Known Activations