© 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. 78968
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions and phrases indicating addition or continuation in discussions

    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
    åº
    -0.07
    ota
    -0.07
    omb
    -0.07
    rous
    -0.06
     Bor
    -0.06
    ynes
    -0.06
    ox
    -0.06
    uentes
    -0.06
    ÑĢÑĥз
    -0.06
    便
    -0.06
    POSITIVE LOGITS
     how
    0.16
    how
    0.12
    å¦Ĥä½ķ
    0.11
     cómo
    0.10
     why
    0.10
     ways
    0.10
    -how
    0.08
     hvordan
    0.08
    why
    0.08
    afil
    0.08
    Activations Density 0.069%

    No Known Activations