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. 23-RESID-POST-AA
    6. 103951
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -risk
    -0.07
    inclu
    -0.07
    NORMAL
    -0.06
    ovies
    -0.06
     symptoms
    -0.06
    arsers
    -0.06
    codile
    -0.06
    itempty
    -0.06
    parer
    -0.06
    .Cancel
    -0.06
    POSITIVE LOGITS
     uncon
    0.06
     PLA
    0.06
     neat
    0.06
    .et
    0.06
     Newsletter
    0.06
     filesystem
    0.06
     здійснення
    0.06
     Spe
    0.06
    anks
    0.06
     PTR
    0.06
    Activations Density 0.067%

    No Known Activations