© 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. 129
    Prev
    Next
    INDEX
    Explanations

    references to equations and mathematical symbols

    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
     Nel
    -0.08
    assi
    -0.07
    uk
    -0.07
     Berry
    -0.06
     Bentley
    -0.06
    $MESS
    -0.06
     MPU
    -0.06
    uko
    -0.06
    민
    -0.06
     Father
    -0.06
    POSITIVE LOGITS
    bjerg
    0.08
    esc
    0.07
    å¼ı
    0.07
    APE
    0.07
    lope
    0.07
    roadcast
    0.06
    ishes
    0.06
    маÑħ
    0.06
     aras
    0.06
    illions
    0.06
    Activations Density 0.092%

    No Known Activations