© 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. 73663
    Prev
    Next
    INDEX
    Explanations

    the name "Shim" in various contexts related to authority or influence

    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
    emble
    -0.07
    ollah
    -0.07
    orate
    -0.07
    sian
    -0.07
    ANEL
    -0.07
    ToOne
    -0.06
    otti
    -0.06
    aits
    -0.06
    ίνα
    -0.06
    beiten
    -0.06
    POSITIVE LOGITS
    WWW
    0.07
    ayı
    0.07
    azz
    0.06
    aler
    0.06
    olik
    0.06
    amura
    0.06
    cher
    0.06
    arts
    0.06
    eway
    0.06
    ethe
    0.06
    Activations Density 0.008%

    No Known Activations