© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 85020
    Prev
    Next
    INDEX
    Explanations

    phrases related to documentation and formal review processes

    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
    canf
    -0.08
    Å¡ov
    -0.08
    _expand
    -0.07
    immer
    -0.07
    ÑĤÑİ
    -0.07
    quier
    -0.07
    atto
    -0.07
    umu
    -0.07
    ÏĦÏģα
    -0.07
    yme
    -0.07
    POSITIVE LOGITS
     decide
    0.09
     decided
    0.09
     decides
    0.09
     if
    0.08
     deciding
    0.08
     report
    0.08
    åĨ³å®ļ
    0.07
     found
    0.07
     eventual
    0.07
     eventually
    0.07
    Activations Density 0.051%

    No Known Activations