© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88285
    Prev
    Next
    INDEX
    Explanations

    references to community participation and support

    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
    onavir
    -0.07
    oyo
    -0.07
    ylon
    -0.07
    avir
    -0.07
    722
    -0.07
    apus
    -0.07
     جاÙħع
    -0.07
    à¹Ħล
    -0.06
    ledge
    -0.06
    alance
    -0.06
    POSITIVE LOGITS
     overnight
    0.06
     deleg
    0.06
     literally
    0.06
    ühl
    0.06
     Bullet
    0.06
     crush
    0.06
     Crush
    0.06
    lah
    0.06
    inent
    0.06
    Uvs
    0.06
    Activations Density 0.007%

    No Known Activations