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. 11-RESID-POST-AA
    6. 50372
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    /group
    -0.06
     tables
    -0.06
     group
    -0.06
     groups
    -0.06
    ,h
    -0.06
     Од
    -0.06
     fucks
    -0.06
    -war
    -0.06
     Ανα
    -0.06
    War
    -0.06
    POSITIVE LOGITS
    website
    0.08
     dizzy
    0.06
    	Model
    0.06
    NOWLED
    0.06
     culmination
    0.06
     disclosing
    0.06
    Liver
    0.06
    лена
    0.06
    	true
    0.06
    uitive
    0.06
    Activations Density 0.010%

    No Known Activations