© 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. 27609
    Prev
    Next
    INDEX
    Explanations

    references to data measurement and assessment within discussions of investments

    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
     Pun
    -0.07
    ollen
    -0.06
     Peyton
    -0.06
    .
    -0.05
    orial
    -0.05
    (
    -0.05
    ucci
    -0.05
    inton
    -0.05
    ivan
    -0.05
    imming
    -0.05
    POSITIVE LOGITS
     Decomp
    0.08
    plx
    0.08
    EFR
    0.07
     jadx
    0.07
    enticate
    0.07
     trá»Ŀi
    0.07
    ì§ĵ
    0.07
    dream
    0.07
     modelBuilder
    0.06
    ladu
    0.06
    Activations Density 0.014%

    No Known Activations