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. 44366
    Prev
    Next
    INDEX
    Explanations

    various forms and references to the word "con."

    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
    entifier
    -0.07
    _COMPILE
    -0.07
    ials
    -0.07
    kı
    -0.07
    ç·
    -0.07
    ieu
    -0.07
    owi
    -0.07
    коз
    -0.07
    onde
    -0.07
    oux
    -0.06
    POSITIVE LOGITS
    cert
    0.23
    CERT
    0.19
    ert
    0.15
     cert
    0.15
    Cert
    0.15
    erts
    0.14
     certs
    0.14
    sert
    0.13
    -cert
    0.13
    erto
    0.13
    Activations Density 0.006%

    No Known Activations