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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118894
    Prev
    Next
    INDEX
    Explanations

    instances of the word "when" to signal temporal events or context

    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
    ÑĮко
    -0.08
    PIO
    -0.07
     totiž
    -0.07
    ÑĢиз
    -0.07
     Ferd
    -0.07
     Einsatz
    -0.07
     nhiên
    -0.07
    ãĥĨãĥ«
    -0.07
    ìĦŃ
    -0.07
    emma
    -0.07
    POSITIVE LOGITS
    zcze
    0.07
     visited
    0.06
     he
    0.06
     earlier
    0.06
     himself
    0.06
     corresponding
    0.06
     became
    0.06
     recently
    0.06
     visits
    0.06
     promising
    0.05
    Activations Density 0.022%

    No Known Activations