© 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. 14509
    Prev
    Next
    INDEX
    Explanations

    terms associated with academic disciplines and fields of study

    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
    ÑĢек
    -0.07
    anka
    -0.07
    iny
    -0.06
    anax
    -0.06
    ixe
    -0.06
    .Actions
    -0.06
    zel
    -0.06
    zan
    -0.06
    _FACT
    -0.06
    anco
    -0.06
    POSITIVE LOGITS
    obi
    0.06
     thereby
    0.06
    513
    0.05
    531
    0.05
     Harold
    0.05
    queryParams
    0.05
    262
    0.05
     даÑĤ
    0.05
    303
    0.05
    elerik
    0.05
    Activations Density 0.003%

    No Known Activations