© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 51879
    Prev
    Next
    INDEX
    Explanations

    injuries and first aid

    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
     appDelegate
    -0.07
    infos
    -0.06
     Winner
    -0.06
    formatted
    -0.06
     deferred
    -0.06
    itas
    -0.06
    ้ค
    -0.06
     comprom
    -0.06
     npc
    -0.06
    arena
    -0.06
    POSITIVE LOGITS
     harassing
    0.07
     combines
    0.06
    .Filter
    0.06
    (WIN
    0.06
     JFactory
    0.06
    utschein
    0.06
     poru
    0.06
    indhoven
    0.06
    getView
    0.06
    ウィ
    0.06
    Activations Density 0.007%

    No Known Activations