© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 26668
    Prev
    Next
    INDEX
    Explanations

    descriptions of ornamental or decorative accessories

    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
    ££
    -0.06
    ê¼
    -0.06
    ást
    -0.06
     dress
    -0.06
    _STRUCT
    -0.06
    _UL
    -0.06
    astic
    -0.06
     loadChildren
    -0.06
     bond
    -0.06
    .unbind
    -0.06
    POSITIVE LOGITS
    andi
    0.07
    abus
    0.07
    opo
    0.07
    TAIL
    0.06
     handmade
    0.06
    onta
    0.06
    eya
    0.06
    uo
    0.06
    bjerg
    0.06
    ki
    0.06
    Activations Density 0.018%

    No Known Activations