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. 122646
    Prev
    Next
    INDEX
    Explanations

    acquisitions

    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
    )";
    ↵
    -0.09
    amba
    -0.07
    227
    -0.06
     登
    -0.06
    登
    -0.06
    	count
    -0.06
     Saddam
    -0.06
    نى
    -0.06
    owner
    -0.06
    .HttpServletResponse
    -0.06
    POSITIVE LOGITS
     acquisitions
    0.09
     setVisible
    0.07
     Cats
    0.07
     clandest
    0.07
    _similarity
    0.07
     Concat
    0.06
    olithic
    0.06
    ุรก
    0.06
    bij
    0.06
     merg
    0.06
    Activations Density 0.014%

    No Known Activations