© 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. 87861
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions

    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
     Therefore
    -0.07
    uiten
    -0.06
    Therefore
    -0.06
    .convert
    -0.06
    oho
    -0.06
     However
    -0.06
     therefore
    -0.06
     nên
    -0.06
    len
    -0.06
     nu
    -0.06
    POSITIVE LOGITS
    berapa
    0.08
     how
    0.08
    Looper
    0.08
    orWhere
    0.07
     çŃĶ
    0.07
    bourg
    0.07
     hvordan
    0.07
     ÙĪØ£ÙĨ
    0.07
    UGIN
    0.07
    Ỽp
    0.07
    Activations Density 0.022%

    No Known Activations