© 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. 38940
    Prev
    Next
    INDEX
    Explanations

    elements related to names and inscriptions

    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
    ê»
    -0.07
    .ToShort
    -0.06
    /live
    -0.06
    land
    -0.06
    erver
    -0.06
    ved
    -0.06
     Wiring
    -0.06
    akh
    -0.06
    åĬ¨çĶŁæĪIJ
    -0.06
     prefixed
    -0.06
    POSITIVE LOGITS
    implify
    0.07
    implified
    0.06
    ffiti
    0.06
    å®ĭä½ĵ
    0.06
    微软éĽħé»ij
    0.06
    à¹Īà¸Ńย
    0.06
    itia
    0.06
    aleigh
    0.06
    ValueCollection
    0.06
     text
    0.06
    Activations Density 0.017%

    No Known Activations