© 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. 88169
    Prev
    Next
    INDEX
    Explanations

    baseball-related terminology and actions

    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
    altar
    -0.07
    928
    -0.07
    982
    -0.06
    hood
    -0.06
    union
    -0.06
    angkan
    -0.06
    ius
    -0.06
    ضاء
    -0.06
    ount
    -0.06
    agua
    -0.06
    POSITIVE LOGITS
    upply
    0.07
    adh
    0.07
    OTE
    0.06
    izyon
    0.06
     Maver
    0.06
    ãĥ³ãĤ°ãĥ«
    0.06
    edis
    0.06
    plen
    0.06
    azor
    0.06
    ossa
    0.06
    Activations Density 0.000%

    No Known Activations