© 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. 3-RESID-POST-AA
    6. 95244
    Prev
    Next
    INDEX
    Explanations

    default

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dispersed
    -0.07
    ekim
    -0.06
     gesch
    -0.06
    (Node
    -0.06
     Bringing
    -0.06
     университ
    -0.06
    exclude
    -0.06
     sagen
    -0.06
    Expansion
    -0.06
     Massive
    -0.06
    POSITIVE LOGITS
     default
    0.21
    default
    0.14
     Default
    0.12
    /default
    0.10
     defaulted
    0.10
    -default
    0.10
    	default
    0.09
    Default
    0.09
    (Default
    0.09
    (default
    0.08
    Activations Density 0.010%

    No Known Activations