© 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. 69547
    Prev
    Next
    INDEX
    Explanations

    references to data structure attributes and their properties

    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
    arget
    -0.07
    ibi
    -0.07
    Triple
    -0.07
    aversal
    -0.06
    lbrace
    -0.06
    ont
    -0.06
    ADER
    -0.06
    Monad
    -0.06
    ociety
    -0.06
     Triple
    -0.06
    POSITIVE LOGITS
     variable
    0.10
    åŃĹ段
    0.08
     variables
    0.08
     пеÑĢемен
    0.08
     field
    0.07
    kke
    0.07
    variable
    0.07
     column
    0.07
    .scalar
    0.06
     Variables
    0.06
    Activations Density 0.024%

    No Known Activations