© 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. 72270
    Prev
    Next
    INDEX
    Explanations

    keywords and technical terms related to web technologies and server configurations

    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
    isque
    -0.10
    ÑĢоÑĪ
    -0.09
    ynos
    -0.08
    reu
    -0.08
    иÑĤов
    -0.08
    assin
    -0.08
    amburg
    -0.08
    isty
    -0.07
    Ħĸ
    -0.07
    åªĴ
    -0.07
    POSITIVE LOGITS
    al
    0.06
    aby
    0.06
     Fay
    0.06
    tic
    0.06
    oom
    0.06
    ](
    0.06
    yo
    0.06
     Carter
    0.06
    <td
    0.06
    ib
    0.05
    Activations Density 0.022%

    No Known Activations