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. 15-RESID-POST-AA
    6. 127507
    Prev
    Next
    INDEX
    Explanations

    articles

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [C
    -0.07
     colore
    -0.07
    (calendar
    -0.06
    olu
    -0.06
     TMZ
    -0.06
    ForKey
    -0.06
     ;)↵↵
    -0.06
    /pi
    -0.06
     Dani
    -0.06
     Yad
    -0.06
    POSITIVE LOGITS
    233
    0.07
    Upload
    0.06
     implicit
    0.06
    	       
    0.06
     INTERVAL
    0.06
    brace
    0.06
     Motion
    0.06
     getName
    0.06
    ──
    0.06
     :],
    0.06
    Activations Density 0.000%

    No Known Activations