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. 11-RESID-POST-AA
    6. 21536
    Prev
    Next
    INDEX
    Explanations

    summary

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demonic
    -0.07
    student
    -0.06
     stamina
    -0.06
    女性
    -0.06
     plaque
    -0.06
    :@""
    -0.06
     hizmet
    -0.06
     brothers
    -0.06
    ेकर
    -0.06
     tail
    -0.06
    POSITIVE LOGITS
    Exporter
    0.07
     arisen
    0.07
    _BC
    0.07
    !
    ↵
    0.07
    (cmp
    0.07
     IDisposable
    0.07
     +↵↵
    0.06
     <$>
    0.06
     νεφοκάλυψης
    0.06
     [<
    0.06
    Activations Density 0.003%

    No Known Activations