© 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. 61701
    Prev
    Next
    INDEX
    Explanations

    occurrences of actions and decisions related to organization and support options

    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
    oot
    -0.08
    _EXTERN
    -0.06
    ozilla
    -0.06
     Å
    -0.06
    kas
    -0.06
    -addons
    -0.06
    emiz
    -0.06
    adio
    -0.06
     Ludwig
    -0.06
    ÅĻÃŃzenÃŃ
    -0.06
    POSITIVE LOGITS
     this
    0.08
    è¿Ļç§į
    0.07
     ÑįÑĤа
    0.07
    this
    0.07
    å®ŀæĸ½
    0.07
    Implement
    0.07
    ãĢģãģĵãģ®
    0.07
     подоб
    0.07
    è¿Ļ个
    0.07
     Implement
    0.07
    Activations Density 0.066%

    No Known Activations