© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 39813
    Prev
    Next
    INDEX
    Explanations

    simplify

    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
     outcry
    -0.07
    โอ
    -0.07
    Dir
    -0.07
    <Vector
    -0.07
     Climate
    -0.06
    otřeb
    -0.06
     Capability
    -0.06
    .Track
    -0.06
     Laure
    -0.06
     Lease
    -0.06
    POSITIVE LOGITS
     streamline
    0.08
    .unsplash
    0.07
     simplified
    0.07
    glyph
    0.06
     simplify
    0.06
     سلام
    0.06
     подоб
    0.06
    ******
    0.06
     Simpl
    0.06
     allev
    0.06
    Activations Density 0.015%

    No Known Activations