© 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. 9-LLAMASCOPE-RES-131K
    11. 95806
    Prev
    Next
    INDEX
    Explanations

    references to visiting or attending places

    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
    iginal
    -0.09
    utsch
    -0.08
    eron
    -0.08
    wart
    -0.07
    uling
    -0.07
    ecycle
    -0.07
    efined
    -0.07
    inine
    -0.07
    coon
    -0.07
    лиÑħ
    -0.07
    POSITIVE LOGITS
    ãģĤãĤĭ
    0.07
    iting
    0.06
     thÄĥm
    0.06
    OrUpdate
    0.06
    hled
    0.06
    ograd
    0.06
    _registro
    0.06
    /ex
    0.06
     frequ
    0.06
    RenderingContext
    0.06
    Activations Density 0.036%

    No Known Activations