© 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. 27826
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking steps in recipes

    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
    ItemCount
    -0.07
    ãģĿ
    -0.07
    .Safe
    -0.06
    finity
    -0.06
    ItemAt
    -0.06
    егоÑĢ
    -0.06
    anova
    -0.06
    ICODE
    -0.06
    edenÃŃ
    -0.06
    ardo
    -0.06
    POSITIVE LOGITS
    397
    0.06
    sta
    0.06
    кÑĥл
    0.06
     designated
    0.06
    -empty
    0.06
     Kerr
    0.06
    aku
    0.06
     boÅŁ
    0.06
    uka
    0.06
    ACC
    0.06
    Activations Density 0.022%

    No Known Activations