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. 102244
    Prev
    Next
    INDEX
    Explanations

    theorems

    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
     Congo
    -0.08
     imperative
    -0.06
    aja
    -0.06
     Blond
    -0.06
    ayah
    -0.06
     merupakan
    -0.06
    isActive
    -0.06
     orm
    -0.06
     tolerate
    -0.06
     widgets
    -0.06
    POSITIVE LOGITS
     cellForRowAtIndexPath
    0.06
     ''.
    0.06
    TeX
    0.06
    něm
    0.06
     золот
    0.05
    saved
    0.05
     bullied
    0.05
     castle
    0.05
    ului
    0.05
     Václav
    0.05
    Activations Density 0.013%

    No Known Activations