© 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. 119118
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and technical processes involved in communication systems

    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
     nouve
    -0.07
    धर
    -0.07
    gnore
    -0.07
     teng
    -0.06
    rlen
    -0.06
    ContentLoaded
    -0.06
    ë¦
    -0.06
    (#
    -0.06
    ÅĻÃŃt
    -0.06
    ulerAngles
    -0.06
    POSITIVE LOGITS
    ìĪł
    0.07
     often
    0.07
    Æ°á»Ŀng
    0.06
     must
    0.06
     may
    0.06
    sak
    0.06
     ought
    0.06
     íĤ¤
    0.06
    AXB
    0.06
    ëŀĢ
    0.06
    Activations Density 0.391%

    No Known Activations