© 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. 89088
    Prev
    Next
    INDEX
    Explanations

    sections related to settings and options in technical documentation

    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
    eyse
    -0.08
    /callback
    -0.07
     kre
    -0.07
    лиÑĪком
    -0.07
    anter
    -0.07
    efon
    -0.06
    ãĥ³ãĤ¸
    -0.06
    riad
    -0.06
    Calibri
    -0.06
    uja
    -0.06
    POSITIVE LOGITS
    724
    0.07
     followed
    0.07
    then
    0.07
    952
    0.07
     then
    0.06
    çĦ¶åIJİ
    0.06
    463
    0.06
    364
    0.06
    021
    0.06
    &
    0.06
    Activations Density 0.006%

    No Known Activations