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. 59866
    Prev
    Next
    INDEX
    Explanations

    if

    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
     Full
    -0.07
    Full
    -0.07
    orů
    -0.07
     Numerous
    -0.06
    (and
    -0.06
    (withDuration
    -0.06
    (or
    -0.06
    MEA
    -0.06
    Second
    -0.06
    işti
    -0.06
    POSITIVE LOGITS
     سیستم
    0.06
     fo
    0.06
     traged
    0.06
     Spiel
    0.06
     téléphone
    0.06
    453
    0.06
     百度收录
    0.06
     ************************************************************************
    0.06
     kolem
    0.06
     sce
    0.06
    Activations Density 0.010%

    No Known Activations