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. 43621
    Prev
    Next
    INDEX
    Explanations

    specific symbols or characters often used in mathematical equations or technical documents

    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
    InstanceOf
    -0.07
    ãĤ¤ãĤº
    -0.07
    ->{'
    -0.07
    aney
    -0.07
    alty
    -0.07
    ely
    -0.07
    .bits
    -0.06
    ivable
    -0.06
    -lfs
    -0.06
    uars
    -0.06
    POSITIVE LOGITS
    bil
    0.09
    brook
    0.07
    fet
    0.07
    angel
    0.07
    reff
    0.07
    ball
    0.06
    not
    0.06
    gest
    0.06
    stad
    0.06
    aleb
    0.06
    Activations Density 0.003%

    No Known Activations