© 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. 60166
    Prev
    Next
    INDEX
    Explanations

    inquiries and requests for information

    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
    sov
    -0.07
    DBG
    -0.07
    stry
    -0.07
    hiba
    -0.07
    cors
    -0.06
    ottes
    -0.06
    endoza
    -0.06
    legate
    -0.06
    ÑĢеÑĪ
    -0.06
    .datab
    -0.06
    POSITIVE LOGITS
     describe
    0.10
     describes
    0.08
     please
    0.07
     describing
    0.07
    TickCount
    0.07
    iglia
    0.07
     explain
    0.06
     descri
    0.06
     Describe
    0.06
    Describe
    0.06
    Activations Density 0.005%

    No Known Activations