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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 76217
    Prev
    Next
    INDEX
    Explanations

    XML code

    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_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
     PRI
    -0.06
    _SW
    -0.06
     जबक
    -0.06
    paque
    -0.06
     Util
    -0.06
    $arity
    -0.06
    Authorities
    -0.05
    LESS
    -0.05
     відвід
    -0.05
     dostate
    -0.05
    POSITIVE LOGITS
    .Ch
    0.07
     Dream
    0.07
     meinen
    0.07
    、ア
    0.07
    .They
    0.07
    鐘
    0.06
    cube
    0.06
     chromat
    0.06
     Rocks
    0.06
     bev
    0.06
    Activations Density 0.006%

    No Known Activations