© 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. 102113
    Prev
    Next
    INDEX
    Explanations

    )

    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
     Leads
    -0.07
     �
    -0.06
    راه
    -0.06
     Brewing
    -0.06
     Class
    -0.06
    _GPU
    -0.06
     BF
    -0.06
    Twig
    -0.06
    вок
    -0.06
     app
    -0.06
    POSITIVE LOGITS
     graffiti
    0.06
     forty
    0.06
     pageIndex
    0.06
    Okay
    0.06
    adera
    0.06
     STATIC
    0.06
    (al
    0.06
    (resource
    0.06
    which
    0.06
    etsy
    0.06
    Activations Density 0.000%

    No Known Activations