© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4133
    Prev
    Next
    INDEX
    Explanations

    significant events or issues in global affairs

    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
    ispers
    -0.07
    å¹²
    -0.07
     Gel
    -0.06
    .sessions
    -0.06
    .oc
    -0.06
     gel
    -0.06
    ially
    -0.06
    ãĥ³ãĥĢ
    -0.06
    iew
    -0.06
    arry
    -0.06
    POSITIVE LOGITS
     PropertyValue
    0.07
    .raises
    0.07
    .slim
    0.07
    prestashop
    0.06
    TRACE
    0.06
    Gro
    0.06
     ÑģÑĤанов
    0.06
    imitive
    0.06
    .AutoScale
    0.06
    _permalink
    0.06
    Activations Density 0.088%

    No Known Activations