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. 22-LLAMASCOPE-RES-131K
    6. 5578
    Prev
    Next
    INDEX
    Explanations

    references to proteins and their characteristics

    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
    -serif
    -0.07
    alars
    -0.07
    yre
    -0.07
    lesi
    -0.07
    iba
    -0.07
    ipel
    -0.07
    roz
    -0.07
    jÅ¡ÃŃ
    -0.07
    crypto
    -0.06
    IBLE
    -0.06
    POSITIVE LOGITS
    aceous
    0.18
    ase
    0.11
    uria
    0.10
    ases
    0.09
    質
    0.09
    acious
    0.09
     kinase
    0.08
    è´¨
    0.08
    /en
    0.08
    /D
    0.06
    Activations Density 0.014%

    No Known Activations