© 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. 258
    Prev
    Next
    INDEX
    Explanations

    terms associated with various fabric arts and crafts, particularly those involving lace and embroidery

    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
     Mercer
    -0.07
    tiles
    -0.07
    rors
    -0.06
    нике
    -0.06
     impeachment
    -0.06
    LBL
    -0.06
    _prepare
    -0.06
     Hath
    -0.06
     Painter
    -0.06
    _NB
    -0.06
    POSITIVE LOGITS
    obus
    0.08
     technique
    0.07
    BASH
    0.07
    oden
    0.07
    ISTRY
    0.07
    ATAB
    0.06
     Ned
    0.06
     pi
    0.06
    ivism
    0.06
     techniques
    0.06
    Activations Density 0.018%

    No Known Activations