© 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. 57842
    Prev
    Next
    INDEX
    Explanations

    actions related to appearances and events within a scene

    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
    Ī
    -0.07
     geil
    -0.07
    ideographic
    -0.07
     treff
    -0.06
    getDisplay
    -0.06
     Bilim
    -0.06
    rgan
    -0.06
    jab
    -0.06
    907
    -0.06
    veloper
    -0.06
    POSITIVE LOGITS
     next
    0.13
     soon
    0.11
    next
    0.09
    (next
    0.09
     nächsten
    0.07
     nxt
    0.07
    ersh
    0.07
    akov
    0.07
    icina
    0.07
    -next
    0.07
    Activations Density 0.036%

    No Known Activations