© 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. 103173
    Prev
    Next
    INDEX
    Explanations

    scientific and medical research topics

    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
    erdale
    -0.08
    imers
    -0.08
    ecast
    -0.07
     otherwise
    -0.07
    urovision
    -0.07
    tual
    -0.07
    rtle
    -0.07
    averse
    -0.07
    peon
    -0.07
    irut
    -0.07
    POSITIVE LOGITS
     kou
    0.07
    ko
    0.07
    omi
    0.06
    ek
    0.06
    ãĤĪãģŃ
    0.06
     NIH
    0.06
     combin
    0.06
    DL
    0.06
    che
    0.06
    ando
    0.06
    Activations Density 0.074%

    No Known Activations