© 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. 15827
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate participation or involvement in actions or events

    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
    å¹
    -0.08
    olina
    -0.07
    ouri
    -0.06
    odon
    -0.06
    arte
    -0.06
    got
    -0.06
    ëįĶëĭĪ
    -0.06
    iÄħ
    -0.06
    алеж
    -0.06
     async
    -0.06
    POSITIVE LOGITS
     efforts
    0.09
     effort
    0.08
     ranks
    0.07
    838
    0.07
     being
    0.07
    Defaults
    0.07
     endeavor
    0.07
    imar
    0.06
    eff
    0.06
    ère
    0.06
    Activations Density 0.012%

    No Known Activations