© 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. 30139
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements related to figures and graphs in documents

    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
     YE
    -0.06
    avan
    -0.06
     granddaughter
    -0.06
    unal
    -0.06
    aley
    -0.06
     instead
    -0.06
    .sys
    -0.05
    _UNIX
    -0.05
     FindObjectOfType
    -0.05
    olini
    -0.05
    POSITIVE LOGITS
    overn
    0.07
    Ð¡Ðł
    0.07
    _cmds
    0.07
    nÃŃk
    0.07
    ocoder
    0.07
    adius
    0.07
    onym
    0.06
    ONY
    0.06
    æĪĴ
    0.06
    cheon
    0.06
    Activations Density 0.013%

    No Known Activations