© 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. 124158
    Prev
    Next
    INDEX
    Explanations

    HTML tags and metadata related to web documentation

    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
     Circus
    -0.07
     discrete
    -0.06
    aign
    -0.06
    letcher
    -0.05
    âĢ¦↵
    -0.05
     âĢ¦↵
    -0.05
    aghetti
    -0.05
     CrossAxisAlignment
    -0.05
    urred
    -0.05
    apped
    -0.05
    POSITIVE LOGITS
     toc
    0.08
    íĴĪ
    0.08
    ëıĦë¡ľ
    0.08
     anale
    0.07
    Âłtom
    0.07
    UseProgram
    0.07
    .netbeans
    0.07
    ulos
    0.07
     alf
    0.07
    å©Ĩ
    0.07
    Activations Density 0.001%

    No Known Activations