© 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. 73555
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "use" in various contexts

    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
     Disp
    -0.07
    atra
    -0.07
    asz
    -0.07
     Township
    -0.06
     Borders
    -0.06
    madan
    -0.06
    orio
    -0.06
     respectively
    -0.06
    enburg
    -0.06
     pari
    -0.06
    POSITIVE LOGITS
    èģ
    0.07
    rio
    0.06
    ournemouth
    0.06
    pla
    0.06
     Seal
    0.06
    ebra
    0.06
    867
    0.06
    ients
    0.06
    UNUSED
    0.06
     electr
    0.06
    Activations Density 0.001%

    No Known Activations