© 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. 31264
    Prev
    Next
    INDEX
    Explanations

    warnings about food safety and cooking practices

    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
    ansi
    -0.10
     INTERRU
    -0.07
    eyn
    -0.07
    asn
    -0.07
    amer
    -0.07
     Preconditions
    -0.07
    ány
    -0.06
    ÏĦÏİ
    -0.06
    apse
    -0.06
    .Fat
    -0.06
    POSITIVE LOGITS
     inherently
    0.07
     may
    0.07
     risks
    0.07
     potentially
    0.07
     Ris
    0.06
    rink
    0.06
    ÙĤد
    0.06
    may
    0.06
    legen
    0.06
    enda
    0.06
    Activations Density 0.025%

    No Known Activations