© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 69233
    Prev
    Next
    INDEX
    Explanations

    s

    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
    	bar
    -0.07
     VAR
    -0.07
     diag
    -0.06
     Ampl
    -0.06
     guit
    -0.06
    	box
    -0.06
     Heaven
    -0.06
    (Q
    -0.06
     ตร
    -0.06
     Diagnostic
    -0.06
    POSITIVE LOGITS
    s
    0.12
    k
    0.08
    �
    0.08
    Ps
    0.08
    �
    0.08
    As
    0.07
    d
    0.07
     amaç
    0.07
    Whats
    0.07
    ั้
    0.07
    Activations Density 0.057%

    No Known Activations