© 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. 15-LLAMASCOPE-RES-131K
    11. 86691
    Prev
    Next
    INDEX
    Explanations

    words related to measurement or assessment

    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
    astes
    -0.06
    lt
    -0.06
    ide
    -0.06
    ci
    -0.06
    logen
    -0.06
    usal
    -0.06
    idy
    -0.06
    asc
    -0.06
     cart
    -0.06
    BBBB
    -0.06
    POSITIVE LOGITS
    лага
    0.07
    hoff
    0.07
     leven
    0.07
    à¸ĩà¸ģ
    0.07
    먼
    0.07
    ï¼¼
    0.07
    .struts
    0.07
    Å¡ek
    0.07
    alars
    0.06
    //{{
    0.06
    Activations Density 0.000%

    No Known Activations