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. 7-RESID-POST-AA
    6. 119664
    Prev
    Next
    INDEX
    Explanations

    Lac

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     спор
    -0.07
     pers
    -0.07
    "})↵
    -0.06
    سازی
    -0.06
    -Л
    -0.06
     hormone
    -0.06
    _SEC
    -0.06
    _ing
    -0.06
     jub
    -0.06
    ogen
    -0.06
    POSITIVE LOGITS
    filepath
    0.06
    <TreeNode
    0.06
    	l
    0.06
    /native
    0.06
     linestyle
    0.06
    .UserService
    0.06
     interp
    0.06
     expecting
    0.06
    anal
    0.06
     fabricated
    0.06
    Activations Density 0.022%

    No Known Activations