© 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. 90226
    Prev
    Next
    INDEX
    Explanations

    components of organizational meetings and planning

    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
    forums
    -0.07
    sey
    -0.06
    831
    -0.06
    zos
    -0.06
    IMS
    -0.06
    pretty
    -0.06
    olls
    -0.06
    zin
    -0.06
    reh
    -0.06
    /runtime
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĥĩãĤ£
    0.08
    ä¸įçŁ¥
    0.07
    aro
    0.07
     olup
    0.07
    /welcome
    0.07
    缼
    0.07
    shint
    0.07
    _COPY
    0.06
    ï¼ľ
    0.06
     Hick
    0.06
    Activations Density 0.003%

    No Known Activations