© 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. 104857
    Prev
    Next
    INDEX
    Explanations

    numeric references or citations within the text

    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
    ary
    -0.07
    iente
    -0.06
    SEQ
    -0.06
    andid
    -0.06
    ç®±
    -0.06
     updateTime
    -0.06
    è²¼
    -0.06
     anc
    -0.06
    ONEY
    -0.06
    üh
    -0.06
    POSITIVE LOGITS
    eldo
    0.07
    CV
    0.06
    apixel
    0.06
    portun
    0.06
    ableView
    0.06
    erdem
    0.06
    acom
    0.06
    ductive
    0.06
     irreversible
    0.06
    serter
    0.06
    Activations Density 0.012%

    No Known Activations