© 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. 105390
    Prev
    Next
    INDEX
    Explanations

    elements related to nature and artistic expression

    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
     will
    -0.07
     may
    -0.06
     new
    -0.06
    award
    -0.06
     latest
    -0.06
    adic
    -0.06
    illa
    -0.06
    ronic
    -0.06
    may
    -0.06
     but
    -0.06
    POSITIVE LOGITS
    år
    0.08
    .scalablytyped
    0.08
    UBLE
    0.07
    bÃŃ
    0.07
    akis
    0.07
    zim
    0.07
    unce
    0.07
    HORT
    0.07
    WARDED
    0.07
     roky
    0.07
    Activations Density 0.056%

    No Known Activations