Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 127385
    Prev
    Next
    INDEX
    Explanations

    postponements and delays

    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
     raises
    -0.07
    Gate
    -0.07
     Drink
    -0.07
    Works
    -0.06
     Clothing
    -0.06
    waves
    -0.06
    iga
    -0.06
    з
    -0.06
    čet
    -0.06
    _ALARM
    -0.06
    POSITIVE LOGITS
    unctuation
    0.07
    (chalk
    0.07
    ----------------------------
    0.07
    ________
    0.06
    	uint
    0.06
    (stypy
    0.06
    ////////////////////////////////
    0.06
     UClass
    0.06
     useSelector
    0.06
     getSupportActionBar
    0.06
    Activations Density 0.073%

    No Known Activations