© 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. 16060
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of places or organizations

    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
     etc
    -0.07
    arium
    -0.06
     numerator
    -0.06
    lessly
    -0.06
    Äħ
    -0.06
     Lud
    -0.05
    ave
    -0.05
    omics
    -0.05
    omic
    -0.05
     nonzero
    -0.05
    POSITIVE LOGITS
    aña
    0.07
    SCO
    0.07
    ÃĹ↵↵
    0.07
    Boxes
    0.07
    ċ
    0.07
    copies
    0.07
    ourg
    0.07
     ÑĥÑģÑĤанавлива
    0.07
    ":[{↵
    0.07
    ilik
    0.07
    Activations Density 0.023%

    No Known Activations