© 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. 124779
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with classifications or identifiers

    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
    xDB
    -0.08
    onet
    -0.08
    ürn
    -0.08
    POP
    -0.07
    .scalablytyped
    -0.07
    esson
    -0.07
    ckill
    -0.07
    iasi
    -0.07
    bris
    -0.07
    egis
    -0.07
    POSITIVE LOGITS
     tie
    0.06
    adaki
    0.06
    int
    0.06
     Veterans
    0.06
    ernet
    0.06
    273
    0.06
    lich
    0.06
    itable
    0.06
     Tie
    0.05
    Caps
    0.05
    Activations Density 0.001%

    No Known Activations