© 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. 106379
    Prev
    Next
    INDEX
    Explanations

    structure and variations in sentence constructions

    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
    /locale
    -0.07
    611
    -0.06
    rophe
    -0.06
    646
    -0.06
    ÙħÛĮÙĨ
    -0.06
    ovÄĽ
    -0.06
    ırak
    -0.06
    .mapbox
    -0.06
    ously
    -0.06
    596
    -0.06
    POSITIVE LOGITS
    estre
    0.07
    ories
    0.07
    alic
    0.07
    imo
    0.06
    ehr
    0.06
    IMO
    0.06
    sing
    0.06
    lef
    0.06
    elve
    0.06
    UV
    0.06
    Activations Density 0.004%

    No Known Activations