© 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 EvalsExportsAPI 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. 76621
    Prev
    Next
    INDEX
    Explanations

    instances of specified numerical dates or timeframes

    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
    Traits
    -0.07
    angelo
    -0.07
    eld
    -0.07
    houette
    -0.06
    .cljs
    -0.06
    ennent
    -0.06
    BackStack
    -0.06
    Åį
    -0.06
    óa
    -0.06
    èm
    -0.06
    POSITIVE LOGITS
    çħ§
    0.07
     Frank
    0.06
    /sbin
    0.06
    /loose
    0.06
    μÏĨ
    0.06
     this
    0.06
     result
    0.06
    unden
    0.06
    produk
    0.06
    zug
    0.06
    Activations Density 0.043%

    No Known Activations