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. 19-RESID-POST-AA
    6. 51907
    Prev
    Next
    INDEX
    Explanations

    library screening

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippets
    -0.07
    Particles
    -0.07
     mundial
    -0.07
     ludicrous
    -0.06
     colomb
    -0.06
     algo
    -0.06
     آلمان
    -0.06
     Damon
    -0.06
    .webkit
    -0.06
     girlfriends
    -0.06
    POSITIVE LOGITS
     approximation
    0.07
    .parallel
    0.06
    ucken
    0.06
    	ret
    0.06
     реб
    0.06
     modne
    0.06
    amber
    0.06
     SZ
    0.06
    apol
    0.06
     szy
    0.06
    Activations Density 0.110%

    No Known Activations