© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 69744
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to audio equipment and testing

    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
    jedn
    -0.06
    iddi
    -0.06
     McB
    -0.06
    DEX
    -0.06
    overview
    -0.06
     Byl
    -0.06
    outil
    -0.06
    ocket
    -0.06
    Ø¢ÙĨ
    -0.06
    رش
    -0.06
    POSITIVE LOGITS
    ãģ¡ãĤĥãĤĵ
    0.07
    ategorical
    0.07
     itself
    0.07
    Ñħови
    0.06
    åıĬåħ¶
    0.06
    EGIN
    0.06
     Ùħذ
    0.06
    arel
    0.06
    ven
    0.06
    urn
    0.06
    Activations Density 0.044%

    No Known Activations