© 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. 1320
    Prev
    Next
    INDEX
    Explanations

    verbs and actions associated with transactions or creative processes in a narrative context

    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
    icari
    -0.07
    RequestMethod
    -0.07
    eniable
    -0.07
    Ïĥμ
    -0.07
    adian
    -0.06
    (DbContext
    -0.06
     Tato
    -0.06
    QUIRE
    -0.06
    lettes
    -0.06
    eeper
    -0.06
    POSITIVE LOGITS
    ัà¸ĩ
    0.07
    reamble
    0.06
     split
    0.06
     only
    0.06
     unusual
    0.06
     rather
    0.06
    å·¨
    0.06
     unconventional
    0.05
     very
    0.05
    0.05
    Activations Density 0.024%

    No Known Activations