© 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. 105781
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and innovation in business contexts

    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
     ciz
    -0.07
    ere
    -0.06
    eel
    -0.06
    atcher
    -0.06
    ãģķãģ¾
    -0.06
    mrt
    -0.06
     dissoci
    -0.06
     spont
    -0.06
    olars
    -0.06
    307
    -0.06
    POSITIVE LOGITS
     folks
    0.07
     <$
    0.07
     typically
    0.07
    Typ
    0.07
    captures
    0.06
    ennie
    0.06
     POLITICO
    0.06
     Fol
    0.06
    mix
    0.06
     increasingly
    0.06
    Activations Density 0.788%

    No Known Activations