© 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. 125187
    Prev
    Next
    INDEX
    Explanations

    technical terms and values related to functions, actions, or resources

    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
    ulur
    -0.07
     pek
    -0.07
     konkrét
    -0.07
     prostitut
    -0.07
    wel
    -0.07
    astle
    -0.07
    .Cloud
    -0.07
    keiten
    -0.07
    emiah
    -0.07
     romant
    -0.07
    POSITIVE LOGITS
     enough
    0.12
     Enough
    0.10
     to
    0.09
     sufficient
    0.09
     ÑĩÑĤобÑĭ
    0.09
     sufficiently
    0.07
     Äijá»ĥ
    0.07
     Ade
    0.07
     suf
    0.07
    ufficient
    0.06
    Activations Density 0.025%

    No Known Activations