© 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. 15-LLAMASCOPE-RES-131K
    11. 61992
    Prev
    Next
    INDEX
    Explanations

    references to prequels or sequels in storytelling

    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
    porto
    -0.07
    opo
    -0.07
    ãĥ«ãĥĪ
    -0.07
    ucus
    -0.07
    apiro
    -0.07
    cÃŃm
    -0.07
    оÑı
    -0.07
    ìĿ¸ì§Ģ
    -0.06
    668
    -0.06
    anela
    -0.06
    POSITIVE LOGITS
     pre
    0.08
     Pre
    0.08
    931
    0.07
     filling
    0.07
     fills
    0.06
    fill
    0.06
    /Foundation
    0.06
    -prepend
    0.06
     origin
    0.06
    (pre
    0.06
    Activations Density 0.009%

    No Known Activations