© 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. 9-LLAMASCOPE-RES-131K
    11. 97951
    Prev
    Next
    INDEX
    Explanations

    terms related to academic progression and enrollment status

    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
    isd
    -0.07
    CodeGen
    -0.07
    виÑĤ
    -0.07
    ering
    -0.07
    meno
    -0.07
    htar
    -0.07
    lope
    -0.07
    rise
    -0.07
    cli
    -0.07
    åĴ¨è¯¢
    -0.07
    POSITIVE LOGITS
    izzo
    0.06
    ting
    0.06
    anners
    0.06
     camouflage
    0.06
    indow
    0.06
    708
    0.06
     material
    0.06
     Roch
    0.06
    uc
    0.06
    n
    0.06
    Activations Density 0.001%

    No Known Activations