© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78094
    Prev
    Next
    INDEX
    Explanations

    2

    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
    gıç
    -0.07
     verwenden
    -0.06
     mell
    -0.06
     Stap
    -0.06
    branch
    -0.06
     Associ
    -0.06
    Job
    -0.06
     accuses
    -0.06
    _MASK
    -0.06
     utilizando
    -0.06
    POSITIVE LOGITS
    2
    0.09
    4
    0.08
    02
    0.08
    3
    0.08
     体
    0.07
    01
    0.07
    tx
    0.07
    1
    0.07
    �
    0.07
    3
    0.07
    Activations Density 0.017%

    No Known Activations