© 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. 128723
    Prev
    Next
    INDEX
    Explanations

    specific software and platform-related terms

    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
     (?)
    -0.07
    iez
    -0.06
     of
    -0.06
    ervers
    -0.06
    adder
    -0.06
    wing
    -0.06
    emaker
    -0.06
    å¶
    -0.06
    ãĥĥãĥĦ
    -0.06
     vert
    -0.06
    POSITIVE LOGITS
    -compatible
    0.08
    /Linux
    0.07
    .COM
    0.07
    ฯ
    0.07
    /TR
    0.07
    ian
    0.07
    /Open
    0.07
    /GL
    0.07
    _VISIBLE
    0.07
    /MIT
    0.07
    Activations Density 0.012%

    No Known Activations