© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 113043
    Prev
    Next
    INDEX
    Explanations

    State

    np_max-act · gemini-2.0-flash

    references to government or legal jurisdictions and formal state/court contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oculus
    -0.06
     "**
    -0.06
    _station
    -0.06
     Secrets
    -0.06
    stats
    -0.06
     elevator
    -0.06
    image
    -0.06
    ison
    -0.06
    Pot
    -0.06
    els
    -0.06
    POSITIVE LOGITS
     ділян
    0.08
     ASSIGN
    0.07
     wit
    0.07
     postings
    0.07
     สำน
    0.07
     различные
    0.07
    _country
    0.06
     Juni
    0.06
     bò
    0.06
    üph
    0.06
    Activations Density 0.010%

    No Known Activations