© 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 EvalsExportsAPI 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. 78473
    Prev
    Next
    INDEX
    Explanations

    references to food storage and preservation techniques

    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
     handed
    -0.06
     Playboy
    -0.06
    ILITIES
    -0.06
     Ach
    -0.06
    rov
    -0.06
    acus
    -0.06
     Associated
    -0.06
    Vu
    -0.06
    pai
    -0.05
    ÐĴС
    -0.05
    POSITIVE LOGITS
     loss
    0.07
    HeaderCode
    0.07
     Loss
    0.07
    onis
    0.07
     Mour
    0.07
     losses
    0.07
    OLDER
    0.06
    IMITER
    0.06
    zung
    0.06
    interest
    0.06
    Activations Density 0.025%

    No Known Activations