© 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. 61650
    Prev
    Next
    INDEX
    Explanations

    statements about community studies and their impacts

    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
     seper
    -0.06
    aign
    -0.06
     es
    -0.06
     var
    -0.06
    หล
    -0.06
    IDA
    -0.06
    nice
    -0.06
    achi
    -0.06
    PER
    -0.06
     Mediterr
    -0.05
    POSITIVE LOGITS
    anness
    0.08
    usch
    0.07
     participant
    0.07
    غÙĦ
    0.07
    swick
    0.07
    ticks
    0.07
    ariate
    0.07
    $__
    0.07
    emouth
    0.07
    otionEvent
    0.07
    Activations Density 0.000%

    No Known Activations