© 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. 72266
    Prev
    Next
    INDEX
    Explanations

    punctuation and speech indicators

    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
    impse
    -0.07
    utter
    -0.06
    aci
    -0.06
    asser
    -0.06
     Surround
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    iddle
    -0.06
     surrounding
    -0.06
     famously
    -0.06
    inson
    -0.06
    POSITIVE LOGITS
    464
    0.07
    μί
    0.07
    oming
    0.07
    iban
    0.07
    quartered
    0.07
    MAIL
    0.07
    ebi
    0.07
    ãĤ¹ãĤ¯
    0.06
    ahan
    0.06
     Meanwhile
    0.06
    Activations Density 0.022%

    No Known Activations