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. 44391
    Prev
    Next
    INDEX
    Explanations

    references related to viral structures and their interactions with host cells

    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
    ascade
    -0.07
     khai
    -0.07
    rego
    -0.07
     Äijoán
    -0.06
    apter
    -0.06
    à¹īà¸Ńà¸Ļ
    -0.06
     formulaire
    -0.06
    ahir
    -0.06
    uzzer
    -0.06
    iž
    -0.06
    POSITIVE LOGITS
     mitochond
    0.14
     Gol
    0.14
     org
    0.13
     cy
    0.12
     vac
    0.12
     gol
    0.12
     nucleus
    0.11
     membr
    0.11
     ves
    0.10
     plast
    0.10
    Activations Density 0.017%

    No Known Activations