© 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. 107997
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structure indicators

    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
    zion
    -0.07
    ÑĹ
    -0.06
    ’ÑĶ
    -0.06
     "***
    -0.06
    .***
    -0.06
    боÑĤ
    -0.06
    rike
    -0.06
     Sanford
    -0.06
    åºľ
    -0.06
    μÏĢο
    -0.06
    POSITIVE LOGITS
    ủa
    0.07
     *
    0.07
    aul
    0.07
    alc
    0.07
    caff
    0.07
    nova
    0.07
    MemoryWarning
    0.07
    =cut
    0.06
    zzle
    0.06
     åī
    0.06
    Activations Density 0.046%

    No Known Activations