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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43572
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to genetic research and development

    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
     eskort
    -0.07
    ENDOR
    -0.07
    ä»ĺãģį
    -0.07
     Mush
    -0.07
    ocê
    -0.06
    crollView
    -0.06
     à¤Ńà¤Ĺ
    -0.06
    klä
    -0.06
    ìķ¡
    -0.06
    маз
    -0.06
    POSITIVE LOGITS
     fin
    0.11
     ornament
    0.09
     ornaments
    0.08
     Finch
    0.08
     bird
    0.08
     birds
    0.08
     pepper
    0.08
     traits
    0.08
     variation
    0.07
     fins
    0.07
    Activations Density 0.009%

    No Known Activations