© 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. 71113
    Prev
    Next
    INDEX
    Explanations

    sentences that indicate narrative actions or events

    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
    ãĥ¬ãĥ¼
    -0.07
    anki
    -0.07
    ãģİ
    -0.07
    RenderTarget
    -0.07
    oltip
    -0.07
    üle
    -0.07
    åĬŁ
    -0.07
    òa
    -0.07
    uet
    -0.07
    _HELPER
    -0.07
    POSITIVE LOGITS
     while
    0.07
     Meanwhile
    0.07
     bem
    0.06
     he
    0.06
     meiden
    0.06
    ãĥ³ãĤ°
    0.06
     comm
    0.06
     meanwhile
    0.06
    ,
    0.06
    ине
    0.06
    Activations Density 0.010%

    No Known Activations