© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    references to community pride and social issues

    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
     new
    -0.07
     newest
    -0.06
    ulary
    -0.06
    logan
    -0.06
     modern
    -0.06
    åĶ¯
    -0.06
    ustil
    -0.06
    apat
    -0.06
     Newest
    -0.06
    .cc
    -0.06
    POSITIVE LOGITS
     vardı
    0.07
    stup
    0.07
    à¹Ģà¸Ħย
    0.07
     ÙĪÙĥاÙĨ
    0.07
    roe
    0.07
    ense
    0.07
     comparatively
    0.07
    illas
    0.06
    ienie
    0.06
    lover
    0.06
    Activations Density 0.021%

    No Known Activations