Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 92923
    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
     заяви
    -0.07
     finder
    -0.07
     Flesh
    -0.07
     travellers
    -0.07
     FM
    -0.07
     Beds
    -0.06
    .ObjectModel
    -0.06
    ři
    -0.06
     쪽
    -0.06
    _html
    -0.06
    POSITIVE LOGITS
    roupe
    0.07
    ertainment
    0.06
    (lock
    0.06
    lijke
    0.06
     edilm
    0.06
     humor
    0.06
    .getPort
    0.06
    فتم
    0.06
     Magick
    0.06
    frei
    0.06
    Activations Density 0.002%

    No Known Activations