© 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. 105442
    Prev
    Next
    INDEX
    Explanations

    text excerpts or references to excerpts in the document

    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
    aida
    -0.07
    cid
    -0.07
    vard
    -0.06
    æk
    -0.06
    utter
    -0.06
    -gnu
    -0.06
    fred
    -0.06
    bar
    -0.06
    amon
    -0.06
    arters
    -0.06
    POSITIVE LOGITS
    ed
    0.10
    ted
    0.09
    ively
    0.08
    pecially
    0.08
     from
    0.08
    aneous
    0.08
    itution
    0.08
    stakes
    0.07
     dari
    0.07
    tings
    0.07
    Activations Density 0.005%

    No Known Activations