© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 116941
    Prev
    Next
    INDEX
    Explanations

    numeric values and mathematical statements related to models and equations

    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
    μι
    -0.07
    bsd
    -0.07
     frau
    -0.07
    adan
    -0.07
    CTR
    -0.06
    agas
    -0.06
    usi
    -0.06
    й
    -0.06
    .Names
    -0.06
    ÑĢап
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
     thus
    0.07
     otherwise
    0.07
     Accordingly
    0.07
     consequently
    0.06
     Consequently
    0.06
     accordingly
    0.06
    thus
    0.06
    okes
    0.06
     gre
    0.06
    Activations Density 0.114%

    No Known Activations