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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 62334
    Prev
    Next
    INDEX
    Explanations

    references to events or actions happening at the beginning or onset of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commissioner
    -0.06
    naire
    -0.06
    Å¡tÃŃ
    -0.06
    念
    -0.06
    oken
    -0.06
     skl
    -0.06
     Champ
    -0.06
     First
    -0.06
    ady
    -0.06
    shiv
    -0.06
    POSITIVE LOGITS
    erset
    0.08
    ruise
    0.07
    yp
    0.07
     Kendrick
    0.07
    orque
    0.07
    wards
    0.07
    तर
    0.06
    rž
    0.06
    greens
    0.06
    enson
    0.06
    Activations Density 0.008%

    No Known Activations