© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 130065
    Prev
    Next
    INDEX
    Explanations

    phrases related to business dealings and negotiations

    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
    .scalablytyped
    -0.07
     [~,
    -0.07
     subsequ
    -0.07
     Britt
    -0.06
     Nero
    -0.06
     amat
    -0.06
     reim
    -0.06
     folds
    -0.06
     Stall
    -0.06
     Grants
    -0.06
    POSITIVE LOGITS
    /stdc
    0.07
    èĸ¬
    0.07
    باÙĨ
    0.07
    odule
    0.07
    æĭĵ
    0.07
    çĴ°
    0.07
    κηÏĤ
    0.07
     Goldberg
    0.07
    度
    0.06
    .epam
    0.06
    Activations Density 0.001%

    No Known Activations