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. 19-RESID-POST-AA
    6. 51407
    Prev
    Next
    INDEX
    Explanations

    separation or multiples

    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
    \:
    -0.06
    雙
    -0.06
     '}';↵
    -0.06
     pearls
    -0.06
    '].$
    -0.06
    <!--↵
    -0.06
    -President
    -0.06
     giorn
    -0.06
    ीब
    -0.06
     kıs
    -0.06
    POSITIVE LOGITS
    (Transaction
    0.07
    (Chat
    0.07
     Events
    0.06
     Internacional
    0.06
    _assigned
    0.06
    -deals
    0.06
     Recovery
    0.06
     Ary
    0.06
     STATS
    0.06
     subdivisions
    0.06
    Activations Density 0.000%

    No Known Activations