© 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. 54175
    Prev
    Next
    INDEX
    Explanations

    inquiries about recipes and cooking instructions

    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
     Companion
    -0.08
    ë°©
    -0.06
    è²Į
    -0.06
    Erot
    -0.06
    ald
    -0.06
    .dsl
    -0.06
    andscape
    -0.06
    ladıģı
    -0.06
     distilled
    -0.06
    uce
    -0.06
    POSITIVE LOGITS
     kids
    0.08
    kids
    0.07
    LOPT
    0.07
     Kids
    0.07
    ere
    0.06
    roj
    0.06
     variant
    0.06
    shal
    0.06
     gul
    0.06
    esz
    0.06
    Activations Density 0.006%

    No Known Activations