© 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. 85206
    Prev
    Next
    INDEX
    Explanations

    references to student government and its structure

    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
    è£
    -0.06
    LETTE
    -0.06
    ferences
    -0.06
    à¥Ģà¤ķ
    -0.06
    æĭ©
    -0.06
    akte
    -0.06
     predicate
    -0.06
    ôm
    -0.06
     WCHAR
    -0.05
    ÄĽr
    -0.05
    POSITIVE LOGITS
     representation
    0.09
     Representation
    0.08
    Representation
    0.08
    representation
    0.08
     voice
    0.07
     represent
    0.07
     REPRESENT
    0.07
    atisfaction
    0.07
     wedge
    0.07
    voice
    0.07
    Activations Density 0.008%

    No Known Activations