© 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 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. 58566
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to mathematical and computational processes

    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
    ovich
    -0.07
    寿
    -0.06
    crm
    -0.06
     вÑĥз
    -0.06
    semicolon
    -0.06
    ivate
    -0.06
    aily
    -0.06
     Legacy
    -0.06
    .scalablytyped
    -0.06
    chsel
    -0.06
    POSITIVE LOGITS
     cancell
    0.07
     cancel
    0.07
     canc
    0.07
    -cancel
    0.07
     cancellation
    0.07
     cancelling
    0.07
     Canc
    0.06
     cancelled
    0.06
    Cancel
    0.06
    вед
    0.06
    Activations Density 0.014%

    No Known Activations