© 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. 127003
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and management structures

    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
    ekim
    -0.07
    achuset
    -0.07
    ickey
    -0.07
    itus
    -0.07
    qli
    -0.07
    agar
    -0.07
    ç³»
    -0.07
    chyb
    -0.06
    riot
    -0.06
    geist
    -0.06
    POSITIVE LOGITS
     by
    0.08
    ableObject
    0.08
    by
    0.07
     separate
    0.07
     ayrı
    0.07
     closely
    0.07
    @n
    0.06
     Gall
    0.06
     entirely
    0.06
    ãĤ¤ãĥī
    0.06
    Activations Density 0.014%

    No Known Activations