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. 27-RESID-POST-AA
    6. 102990
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rotation
    -0.08
     Rotation
    -0.08
    團
    -0.07
    。↵
    -0.06
    	
    -0.06
    队
    -0.06
     hangs
    -0.06
     bell
    -0.06
     lock
    -0.06
    )。↵
    -0.06
    POSITIVE LOGITS
    .Symbol
    0.07
    ERAL
    0.06
    (DEBUG
    0.06
    nav
    0.06
    PMC
    0.06
     PMC
    0.06
    _COD
    0.06
    ็ก
    0.06
     amacı
    0.06
     artificially
    0.06
    Activations Density 0.083%

    No Known Activations