© 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. 126054
    Prev
    Next
    INDEX
    Explanations

    references to physical objects and their characteristics

    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
    inois
    -0.07
    ptal
    -0.06
    space
    -0.06
     SPACE
    -0.06
     Offices
    -0.06
     ÐĵоÑĢ
    -0.05
    迹
    -0.05
     rooft
    -0.05
    modules
    -0.05
    ENCH
    -0.05
    POSITIVE LOGITS
    rosse
    0.07
     outs
    0.07
    iece
    0.07
    OSP
    0.07
    åľ¨çº¿è§Ĥçľĭ
    0.07
    anton
    0.07
    айÑĤ
    0.07
    heid
    0.07
    handleRequest
    0.07
     Courier
    0.07
    Activations Density 0.001%

    No Known Activations