© 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. 95148
    Prev
    Next
    INDEX
    Explanations

    specifics about devices, particularly their features and specifications

    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
     Usage
    -0.06
    ington
    -0.06
     usage
    -0.06
    yen
    -0.06
     USED
    -0.06
     flexGrow
    -0.06
     Used
    -0.06
     involvement
    -0.06
    $MESS
    -0.06
    urum
    -0.06
    POSITIVE LOGITS
    лÑĥÑĩ
    0.07
    -available
    0.07
     features
    0.07
    features
    0.06
    ç¶
    0.06
     ÙĦÙĨ
    0.06
     feature
    0.06
    AREN
    0.06
    elsen
    0.06
    ãĥ¼ãĥĪ
    0.06
    Activations Density 0.017%

    No Known Activations