© 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. 7-RESID-POST-AA
    6. 113734
    Prev
    Next
    INDEX
    Explanations

    of

    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
    setup
    -0.06
     captive
    -0.06
    랫
    -0.06
    	RT
    -0.06
     कम
    -0.06
     predators
    -0.06
    やって
    -0.06
     상대
    -0.06
    $get
    -0.06
     사람
    -0.06
    POSITIVE LOGITS
    awe
    0.07
     materially
    0.07
    Dr
    0.07
     mozilla
    0.07
     월
    0.07
     wrath
    0.06
     海
    0.06
     Skin
    0.06
     обуч
    0.06
     ******************************************************************************/↵
    0.06
    Activations Density 0.016%

    No Known Activations