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. 43697
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate numerical or quantitative information

    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
     which
    -0.11
     of
    -0.10
     a
    -0.10
     докÑĥм
    -0.10
     that
    -0.10
     and
    -0.10
    1
    -0.08
     the
    -0.08
    2
    -0.08
     ÑĤабли
    -0.08
    POSITIVE LOGITS
     Ñĥже
    0.13
     в
    0.12
     ÑģÑĢазÑĥ
    0.12
     во
    0.12
     ÑĤам
    0.12
     ÑĢанÑĮÑĪе
    0.12
     на
    0.12
     ÑĤолÑĮко
    0.12
     вов
    0.12
     по
    0.12
    Activations Density 0.040%

    No Known Activations