© 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. 41525
    Prev
    Next
    INDEX
    Explanations

    references to exhibitions and artistic showcases

    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
    érica
    -0.09
    anova
    -0.07
    echa
    -0.07
    aub
    -0.07
     !***
    -0.07
    ÑģÑĥÑĤ
    -0.06
    estre
    -0.06
     bý
    -0.06
    igli
    -0.06
    bish
    -0.06
    POSITIVE LOGITS
     focus
    0.08
    nde
    0.08
    focus
    0.08
     focused
    0.07
    runner
    0.07
    immel
    0.07
     focuses
    0.06
    ic
    0.06
    focused
    0.06
     foc
    0.06
    Activations Density 0.048%

    No Known Activations