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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119179
    Prev
    Next
    INDEX
    Explanations

    references to infrastructure development

    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
    -fashioned
    -0.08
    è¾°
    -0.07
    ت
    -0.07
     æľŁ
    -0.07
    isan
    -0.07
    esModule
    -0.07
    /respond
    -0.07
    abyrinth
    -0.07
    isen
    -0.07
    åijĺ
    -0.07
    POSITIVE LOGITS
    urally
    0.08
    alist
    0.07
    -wide
    0.07
    ToFit
    0.07
     heav
    0.07
    sing
    0.06
    0.06
    472
    0.06
    ordinary
    0.06
    ively
    0.06
    Activations Density 0.007%

    No Known Activations