© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 61996
    Prev
    Next
    INDEX
    Explanations

    Arguments and references

    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
    _advance
    -0.07
    children
    -0.06
    \Factory
    -0.06
    ováním
    -0.06
    erties
    -0.06
     refusing
    -0.06
    remely
    -0.06
     публі
    -0.06
    -services
    -0.06
    彩票
    -0.06
    POSITIVE LOGITS
     sebep
    0.07
     neden
    0.06
     Nile
    0.06
    収
    0.06
     equivalence
    0.06
     sequential
    0.06
     nhật
    0.06
    RowAtIndexPath
    0.06
     ///</
    0.06
     оди
    0.06
    Activations Density 0.013%

    No Known Activations