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. 43982
    Prev
    Next
    INDEX
    Explanations

    punctuated contractions and quotations used in conversational contexts

    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
    cht
    -0.06
    anan
    -0.06
    "http
    -0.06
     isNaN
    -0.06
     gec
    -0.06
    cio
    -0.06
    osci
    -0.06
    [of
    -0.06
    anden
    -0.06
    -thumbnails
    -0.06
    POSITIVE LOGITS
    );$
    0.11
    Ë
    0.10
    woke
    0.09
    996
    0.08
    08
    0.08
    068
    0.08
    902
    0.08
    pedo
    0.08
    09
    0.08
    07
    0.08
    Activations Density 0.041%

    No Known Activations