© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126019
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to effects or impacts

    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
    æĪ¶
    -0.07
    coles
    -0.07
    ưá»Ŀng
    -0.07
    ocz
    -0.07
    _defs
    -0.07
    vise
    -0.07
    esters
    -0.07
    cede
    -0.07
    اÙħÛĮ
    -0.07
    ities
    -0.06
    POSITIVE LOGITS
     overall
    0.07
    ema
    0.07
     behalf
    0.07
    -alist
    0.06
     our
    0.06
     finances
    0.06
     the
    0.06
     proceedings
    0.06
     negotiations
    0.06
    ocrine
    0.06
    Activations Density 0.017%

    No Known Activations