© 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. 70406
    Prev
    Next
    INDEX
    Explanations

    phrases related to business partnerships and legal structures

    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
     subrange
    -0.06
     subsidy
    -0.06
    ako
    -0.06
    ologna
    -0.06
    à¹Ģหà¸Ļ
    -0.06
    ocate
    -0.06
     Pok
    -0.06
    unft
    -0.05
    éĥ¨éŨ
    -0.05
     Pry
    -0.05
    POSITIVE LOGITS
     formed
    0.09
     whose
    0.08
     formation
    0.08
    naire
    0.07
     created
    0.07
    whose
    0.07
     nomin
    0.07
     Gors
    0.07
    ady
    0.07
    veau
    0.07
    Activations Density 0.018%

    No Known Activations