© 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. 124159
    Prev
    Next
    INDEX
    Explanations

    terms related to current values and parameters in technical and scientific 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
    ĸī
    -0.07
    康
    -0.07
    vince
    -0.07
    综åIJĪ
    -0.06
     Roose
    -0.06
     Rev
    -0.06
    EndPoint
    -0.06
    (cos
    -0.06
    ÑĢаÑħов
    -0.06
    plug
    -0.06
    POSITIVE LOGITS
     versions
    0.09
     version
    0.09
     kinds
    0.09
     aspects
    0.09
     amount
    0.08
     types
    0.08
     aspect
    0.08
     portion
    0.08
     level
    0.08
     instances
    0.07
    Activations Density 0.139%

    No Known Activations