© 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. 62270
    Prev
    Next
    INDEX
    Explanations

    descriptions of dining experiences and restaurant atmospheres

    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
    .scalablytyped
    -0.07
    aria
    -0.07
     auction
    -0.06
     resultant
    -0.06
    AGR
    -0.06
    gettext
    -0.06
     Farmer
    -0.06
    ær
    -0.05
     ÏĥÏħγκ
    -0.05
    dney
    -0.05
    POSITIVE LOGITS
     inicial
    0.07
     debut
    0.06
    oin
    0.06
     initial
    0.06
    797
    0.06
     رسÙħ
    0.06
    TriState
    0.06
     initially
    0.06
    roat
    0.06
    ÑģиÑĤ
    0.06
    Activations Density 0.013%

    No Known Activations