© 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. 15-LLAMASCOPE-RES-131K
    11. 61614
    Prev
    Next
    INDEX
    Explanations

    numerical ratings and user review metrics

    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
    ander
    -0.08
    winner
    -0.06
    immer
    -0.06
     f
    -0.06
    esel
    -0.06
    asar
    -0.06
     (
    -0.06
    anders
    -0.06
     cat
    -0.06
    vi
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    abaj
    0.08
    @ResponseBody
    0.07
     addCriterion
    0.07
    기ì¤Ģ
    0.07
     RENDER
    0.07
    ÑĢей
    0.07
    RAINT
    0.06
     UITextField
    0.06
    ookie
    0.06
    Activations Density 0.006%

    No Known Activations