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. 43990
    Prev
    Next
    INDEX
    Explanations

    mentions of mechanical or engineering-related terms

    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
    eed
    -0.08
    unbind
    -0.07
    γη
    -0.06
    orna
    -0.06
    _errno
    -0.06
     Territories
    -0.06
     Rift
    -0.06
    jsc
    -0.06
    á»±
    -0.06
    ALLY
    -0.06
    POSITIVE LOGITS
    anical
    0.24
    anism
    0.19
    anic
    0.17
    ancial
    0.13
    an
    0.13
    anik
    0.12
    atron
    0.12
    anos
    0.12
    inery
    0.11
    ano
    0.11
    Activations Density 0.003%

    No Known Activations