© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 27524
    Prev
    Next
    INDEX
    Explanations

    phrases related to corporate performance and issues

    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
    å¾ĭ
    -0.07
    oire
    -0.07
    ocabulary
    -0.07
    imeo
    -0.06
    RYPTO
    -0.06
    Äįin
    -0.06
    erdale
    -0.06
    ãĥªãĤ«
    -0.06
    ãĤ¤ãĤ¯
    -0.06
    FE
    -0.06
    POSITIVE LOGITS
    egl
    0.07
    олж
    0.07
     losses
    0.07
    ouch
    0.06
    mouseleave
    0.06
     ICON
    0.06
    ruc
    0.06
    empor
    0.06
    loss
    0.06
    ÙĪÙħاÙĨ
    0.06
    Activations Density 0.009%

    No Known Activations