© 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. 70913
    Prev
    Next
    INDEX
    Explanations

    references to events and experiences related to communal and celebratory settings

    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
    _Tis
    -0.07
    gross
    -0.07
    ìĿ´ê³ł
    -0.07
     Ä°z
    -0.07
    ’↵↵
    -0.07
     whilst
    -0.07
    iets
    -0.07
    lacak
    -0.07
    .scalablytyped
    -0.07
    reffen
    -0.07
    POSITIVE LOGITS
     finally
    0.07
     importantly
    0.06
    itan
    0.06
     willingness
    0.06
    amble
    0.06
    allen
    0.06
     (
    0.06
     Finally
    0.05
     willing
    0.05
     gal
    0.05
    Activations Density 0.047%

    No Known Activations