© 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. 17-LLAMASCOPE-RES-131K
    11. 124537
    Prev
    Next
    INDEX
    Explanations

    legal case citations

    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
    ither
    -0.08
     Bolton
    -0.06
    igit
    -0.06
     cigarette
    -0.06
    rey
    -0.06
    /ui
    -0.06
    ÑĨионалÑĮ
    -0.06
    ologne
    -0.06
    ullan
    -0.06
    ĥn
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĤº
    0.07
    ÑĢок
    0.07
    assis
    0.07
    agram
    0.06
     Doe
    0.06
    TickCount
    0.06
    egra
    0.06
    ãģŁãģĹ
    0.06
    asio
    0.06
     Fallen
    0.06
    Activations Density 0.006%

    No Known Activations