© 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. 15-LLAMASCOPE-RES-131K
    11. 89855
    Prev
    Next
    INDEX
    Explanations

    concepts related to strength training and muscle building

    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
    ancode
    -0.06
    esco
    -0.06
    _INITIAL
    -0.06
    anno
    -0.06
    asca
    -0.06
     waive
    -0.06
     corners
    -0.06
    oÄį
    -0.06
     Elo
    -0.06
    _RESERVED
    -0.06
    POSITIVE LOGITS
    amping
    0.07
    _firestore
    0.07
     Sculpt
    0.07
    icina
    0.07
     training
    0.06
     sculpt
    0.06
    targets
    0.06
    utes
    0.06
    ainers
    0.06
     schedules
    0.06
    Activations Density 0.002%

    No Known Activations