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. 44273
    Prev
    Next
    INDEX
    Explanations

    references to machinery and operational processes

    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
    rezent
    -0.06
     Ðŀдна
    -0.06
     happier
    -0.06
    /nav
    -0.05
     ÑĢаÑģпÑĢоÑģÑĤ
    -0.05
    .scalablytyped
    -0.05
    ä»ĬæĹ¥
    -0.05
    ccoli
    -0.05
     hoá
    -0.05
     xxxx
    -0.05
    POSITIVE LOGITS
    Ñģ
    0.09
     С
    0.08
     Ðľ
    0.08
     («
    0.08
     âĦĸ
    0.08
     Ðļ
    0.08
     schemes
    0.08
     Т
    0.07
     «
    0.07
     technological
    0.07
    Activations Density 0.025%

    No Known Activations