© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126625
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "today."

    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
     Mara
    -0.07
    erview
    -0.07
    Ãłm
    -0.07
    еÑı
    -0.07
    899
    -0.07
    sey
    -0.07
     Kurum
    -0.06
    ieri
    -0.06
    phem
    -0.06
    vern
    -0.06
    POSITIVE LOGITS
     PIO
    0.07
    |array
    0.06
    ableObject
    0.06
    avin
    0.06
    ħ
    0.06
    inux
    0.06
    PLUS
    0.06
    _plugins
    0.06
    .increment
    0.06
    inox
    0.06
    Activations Density 0.000%

    No Known Activations