Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95854
    Prev
    Next
    INDEX
    Explanations

    terms related to nanotechnology and its applications

    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
    ë¡ł
    -0.07
    ãĥ³ãĥĪ
    -0.07
     Nice
    -0.06
    axy
    -0.06
    óz
    -0.06
    uran
    -0.06
    nea
    -0.06
    ugar
    -0.06
    iene
    -0.06
    504
    -0.06
    POSITIVE LOGITS
    gram
    0.08
    alink
    0.07
    -scale
    0.07
    /local
    0.07
    lify
    0.07
    íıIJ
    0.06
    /small
    0.06
     Inhal
    0.06
    /Instruction
    0.06
    kins
    0.06
    Activations Density 0.004%

    No Known Activations