© 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. 40677
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to mathematics and physics

    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
    ames
    -0.07
    possibly
    -0.06
    conde
    -0.06
    ptions
    -0.06
    ober
    -0.06
    otron
    -0.05
    hydrate
    -0.05
    _nl
    -0.05
    rant
    -0.05
    alias
    -0.05
    POSITIVE LOGITS
    ãģ¨ãģ¯
    0.09
     means
    0.09
    ãĤ¤ãĥī
    0.08
    means
    0.08
    ierz
    0.07
    å°±æĺ¯
    0.07
     definition
    0.07
     عبارت
    0.07
     simply
    0.07
    iph
    0.07
    Activations Density 0.054%

    No Known Activations