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. 11-RESID-POST-AA
    6. 100226
    Prev
    Next
    INDEX
    Explanations

    clock

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SAR
    -0.08
     aden
    -0.08
     Hardy
    -0.08
     Weinstein
    -0.07
    262
    -0.07
     Panda
    -0.07
     Parad
    -0.07
     vari
    -0.07
    it
    -0.07
    -rad
    -0.07
    POSITIVE LOGITS
     clock
    0.13
     Clock
    0.11
    Clock
    0.10
    -clock
    0.09
    (clock
    0.09
     clocks
    0.09
     CLOCK
    0.08
    clock
    0.08
    ुख
    0.07
    	clock
    0.07
    Activations Density 0.006%

    No Known Activations