© 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. 17-LLAMASCOPE-RES-131K
    11. 3462
    Prev
    Next
    INDEX
    Explanations

    phrases and keywords related to copyright and licensing conditions

    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
    [
    -0.07
    <
    -0.06
    h
    -0.06
    -
    -0.06
    obus
    -0.06
    uv
    -0.06
    622
    -0.06
    j
    -0.05
    ou
    -0.05
     qu
    -0.05
    POSITIVE LOGITS
    è³Ģ
    0.08
    екаÑĢ
    0.08
    EndInit
    0.08
    /Instruction
    0.07
    thenReturn
    0.07
    .googlecode
    0.07
     ++)
    0.07
     Redistributions
    0.07
    pyx
    0.07
     меÑħ
    0.07
    Activations Density 0.002%

    No Known Activations