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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128479
    Prev
    Next
    INDEX
    Explanations

    references to academic studies or authors

    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
    еÑĢ
    -0.08
    оÑĢ
    -0.08
    rid
    -0.08
    ен
    -0.08
    old
    -0.08
    ro
    -0.07
    ron
    -0.07
    ر
    -0.07
    uns
    -0.07
    ui
    -0.07
    POSITIVE LOGITS
    elin
    0.08
    oni
    0.07
    lee
    0.07
    ATE
    0.07
    -force
    0.06
    omi
    0.06
    inz
    0.06
    localized
    0.06
    opher
    0.06
    heit
    0.06
    Activations Density 0.137%

    No Known Activations