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. 44253
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and statements made by individuals about their lives

    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
     Spacer
    -0.06
    ãĤıãģŁãģĹ
    -0.06
     aalborg
    -0.06
    TOTYPE
    -0.06
    kits
    -0.06
    á»Ĺng
    -0.06
    hend
    -0.06
    ukt
    -0.06
    urat
    -0.06
     NUIT
    -0.06
    POSITIVE LOGITS
     fans
    0.13
     TMZ
    0.10
     sources
    0.10
     model
    0.10
    fans
    0.10
     PEOPLE
    0.09
     pap
    0.09
     viewers
    0.09
     fian
    0.09
     host
    0.09
    Activations Density 0.060%

    No Known Activations