© 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. 15394
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements and dimensions

    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
    ris
    -0.08
    irt
    -0.07
    irse
    -0.07
    ove
    -0.06
    Neill
    -0.06
     inscription
    -0.06
    Slash
    -0.06
    irc
    -0.06
    oola
    -0.06
    hoo
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
     Misc
    0.07
     ----------------------------------------------------------------------------↵
    0.07
     Blow
    0.07
     gallons
    0.06
    _nbr
    0.06
    imler
    0.06
    /MPL
    0.06
    å®Ļ
    0.06
    _misc
    0.06
    Activations Density 0.068%

    No Known Activations