© 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. 57412
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to collaboration and technology

    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
    ách
    -0.08
    claimer
    -0.07
    uries
    -0.07
    //{{
    -0.07
     tá»ĭch
    -0.07
    hta
    -0.07
    AMPL
    -0.07
    екÑĤив
    -0.07
    ิà¹Ģว
    -0.07
    rames
    -0.07
    POSITIVE LOGITS
     Alman
    0.06
    iper
    0.06
     kaf
    0.06
     german
    0.06
     Glob
    0.06
     weighted
    0.05
     Starter
    0.05
     pec
    0.05
    attro
    0.05
     glo
    0.05
    Activations Density 0.001%

    No Known Activations