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. 112804
    Prev
    Next
    INDEX
    Explanations

    surgical

    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
     KO
    -0.07
     trains
    -0.06
     collateral
    -0.06
    lep
    -0.06
    -key
    -0.06
     casualties
    -0.06
     independent
    -0.06
     compliant
    -0.06
     رضا
    -0.06
     Lew
    -0.06
    POSITIVE LOGITS
    XPath
    0.07
    	ft
    0.06
    ится
    0.06
    emie
    0.06
     worse
    0.06
    ạt
    0.06
    _used
    0.06
     arrive
    0.06
    num
    0.06
    036
    0.06
    Activations Density 0.010%

    No Known Activations