© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 116755
    Prev
    Next
    INDEX
    Explanations

    references to software capabilities and features

    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
    .Ribbon
    -0.06
    ,
    -0.06
    -widgets
    -0.06
    odom
    -0.06
    dy
    -0.06
    /trunk
    -0.06
     having
    -0.06
    ibox
    -0.06
     et
    -0.05
     something
    -0.05
    POSITIVE LOGITS
    'gc
    0.09
    software
    0.08
     software
    0.08
    ftware
    0.07
    panion
    0.07
     Záp
    0.07
    chnitt
    0.07
    оÑĢоÑĤ
    0.07
    _DEPRECATED
    0.07
    oftware
    0.07
    Activations Density 0.024%

    No Known Activations