© 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. 14841
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or presence of something

    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
    ewe
    -0.08
    pector
    -0.07
    ounty
    -0.07
    982
    -0.06
    overrides
    -0.06
     Armour
    -0.06
     Dexter
    -0.06
    lias
    -0.06
    oded
    -0.06
    mand
    -0.06
    POSITIVE LOGITS
    loon
    0.07
    .TextAlignment
    0.07
     Harm
    0.06
    oha
    0.06
    uien
    0.06
    bro
    0.06
    PLICATE
    0.06
     two
    0.06
    زد
    0.06
     Hakk
    0.06
    Activations Density 0.016%

    No Known Activations