© 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. 39419
    Prev
    Next
    INDEX
    Explanations

    references to historical or mythical entities and their significance

    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
     baz
    -0.07
    letic
    -0.07
    ench
    -0.07
    çĶº
    -0.07
    ť
    -0.07
    istrat
    -0.07
    antz
    -0.07
    uliar
    -0.07
    ediator
    -0.07
    anness
    -0.06
    POSITIVE LOGITS
    kker
    0.06
     Construct
    0.06
    akh
    0.06
    ua
    0.06
    usal
    0.06
     Constructs
    0.06
     "..
    0.05
    ISP
    0.05
    gel
    0.05
    lesi
    0.05
    Activations Density 0.008%

    No Known Activations