© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88131
    Prev
    Next
    INDEX
    Explanations

    statistical data or figures related to production and consumption

    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
    iffin
    -0.07
    lemn
    -0.06
    pagen
    -0.06
    aben
    -0.06
    egie
    -0.06
    assel
    -0.06
    enge
    -0.06
    etu
    -0.06
    Dot
    -0.06
    ongan
    -0.06
    POSITIVE LOGITS
    habit
    0.06
    ERRU
    0.06
    å¼Ħ
    0.06
    utral
    0.06
     Ulus
    0.06
    chal
    0.06
     Leisure
    0.06
    Hang
    0.06
     versus
    0.06
    quil
    0.06
    Activations Density 0.000%

    No Known Activations