© 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. 38757
    Prev
    Next
    INDEX
    Explanations

    references to product labels and retail conditions

    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
    icon
    -0.06
    amak
    -0.06
     steep
    -0.06
    åĮ
    -0.06
     daleko
    -0.06
    idon
    -0.06
    eg
    -0.06
    ainment
    -0.06
     Wiring
    -0.06
    ember
    -0.06
    POSITIVE LOGITS
     seals
    0.10
     label
    0.09
     Labels
    0.08
     seal
    0.08
     Seal
    0.08
     aff
    0.08
     labels
    0.08
     intact
    0.08
    Label
    0.08
     Label
    0.07
    Activations Density 0.019%

    No Known Activations