© 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. 40269
    Prev
    Next
    INDEX
    Explanations

    prepositions and references to online platforms or resources

    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
    ÃŃv
    -0.07
    quir
    -0.07
    atty
    -0.07
    ÑĪÑĤ
    -0.07
     Courier
    -0.06
    chai
    -0.06
    claimer
    -0.06
    Ỽt
    -0.06
    atar
    -0.06
    ucci
    -0.06
    POSITIVE LOGITS
    kt
    0.07
     ÙħØ®
    0.06
     authDomain
    0.06
    796
    0.06
    oles
    0.06
    792
    0.06
    ende
    0.06
     Açık
    0.06
     UClass
    0.06
     ÑģайÑĤÑĸ
    0.06
    Activations Density 0.003%

    No Known Activations