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. 24133
    Prev
    Next
    INDEX
    Explanations

    evacuation

    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
     unlimited
    -0.07
     limitless
    -0.07
     tech
    -0.07
     tablet
    -0.07
    ания
    -0.06
     mezi
    -0.06
     Ther
    -0.06
     leisure
    -0.06
     shirts
    -0.06
    SCRI
    -0.06
    POSITIVE LOGITS
     evacuate
    0.15
     evacuated
    0.13
     evacuation
    0.11
     evac
    0.11
    áv
    0.07
     excav
    0.07
     вак
    0.07
     Украї
    0.07
    ')}</
    0.07
    VERT
    0.07
    Activations Density 0.003%

    No Known Activations