© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125850
    Prev
    Next
    INDEX
    Explanations

    numerical data related to demographics or statistics

    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
    249
    -0.06
    -0.06
    ments
    -0.06
     term
    -0.06
    illet
    -0.06
    ÙģÙĪ
    -0.05
     smooth
    -0.05
     -
    -0.05
     Bai
    -0.05
     shade
    -0.05
    POSITIVE LOGITS
    elik
    0.08
    \Mapping
    0.08
     metic
    0.07
    برÛĮ
    0.07
     kontro
    0.07
     popis
    0.07
     Obrázky
    0.07
    _GC
    0.07
     didFinish
    0.07
    èģĶç½ij
    0.07
    Activations Density 0.002%

    No Known Activations