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. 44000
    Prev
    Next
    INDEX
    Explanations

    the presence of specific chemical or scientific terms and symbols

    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
     OG
    -0.07
     girls
    -0.06
    Âł
    -0.06
     girl
    -0.06
     D
    -0.06
     GIR
    -0.06
     DK
    -0.05
     R
    -0.05
     track
    -0.05
     DJ
    -0.05
    POSITIVE LOGITS
     pian
    0.11
     Mozart
    0.10
    Opera
    0.10
     Classical
    0.10
     Festival
    0.10
     concerts
    0.10
     Aspen
    0.10
     Opera
    0.10
     chamber
    0.10
    concert
    0.09
    Activations Density 0.003%

    No Known Activations