© 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. 72303
    Prev
    Next
    INDEX
    Explanations

    terms related to database interactions and query errors

    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
    reeze
    -0.07
    ãģĹãĤĩ
    -0.07
     Hatch
    -0.07
    PILE
    -0.07
    celed
    -0.07
    svc
    -0.06
    μμα
    -0.06
    ÅĽcie
    -0.06
    ptal
    -0.06
    érica
    -0.06
    POSITIVE LOGITS
    werk
    0.06
     stanza
    0.06
    inium
    0.06
     bin
    0.06
    Alert
    0.06
    DMI
    0.06
     TICK
    0.06
    plex
    0.06
     Bin
    0.06
     collector
    0.06
    Activations Density 0.021%

    No Known Activations