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. 44163
    Prev
    Next
    INDEX
    Explanations

    strings or sequences related to system or programming codes

    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
     the
    -0.12
     a
    -0.11
     and
    -0.11
     S
    -0.11
     E
    -0.11
     in
    -0.10
     T
    -0.10
     O
    -0.10
     I
    -0.10
     N
    -0.10
    POSITIVE LOGITS
    ilver
    0.15
    ervlet
    0.13
    erge
    0.13
    ШÐIJ
    0.13
    usan
    0.13
    arah
    0.13
    antiago
    0.13
    igma
    0.13
    imon
    0.13
    andbox
    0.12
    Activations Density 0.013%

    No Known Activations