© 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. 17-LLAMASCOPE-RES-131K
    11. 29205
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and metrics

    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
    еÑĢап
    -0.07
    ileÅŁ
    -0.07
    esi
    -0.07
    ůl
    -0.07
    ChangedEventArgs
    -0.07
    óst
    -0.06
    rray
    -0.06
    loor
    -0.06
    UBLE
    -0.06
     ($("#
    -0.06
    POSITIVE LOGITS
     total
    0.09
    Total
    0.07
     Total
    0.07
     count
    0.07
    _total
    0.07
    -total
    0.07
    infra
    0.07
     عدد
    0.06
     avg
    0.06
     ave
    0.06
    Activations Density 0.028%

    No Known Activations