© 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. 72841
    Prev
    Next
    INDEX
    Explanations

    error codes and statuses related to application logs

    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
     Daly
    -0.07
     ruin
    -0.06
     Ub
    -0.06
     Hamm
    -0.06
    591
    -0.06
    aday
    -0.06
     Fields
    -0.06
    836
    -0.06
     pip
    -0.06
     Fell
    -0.06
    POSITIVE LOGITS
    lluminate
    0.07
    thora
    0.07
    opard
    0.07
     Gors
    0.06
    theon
    0.06
    วรรà¸ĵ
    0.06
    -plugins
    0.06
    /graphql
    0.06
    _ENDIAN
    0.06
    illance
    0.06
    Activations Density 0.003%

    No Known Activations