© 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. 17-LLAMASCOPE-RES-131K
    11. 57646
    Prev
    Next
    INDEX
    Explanations

    the word "probably" and its variations, indicating uncertainty

    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
    finder
    -0.09
    à¸Ńาà¸Ī
    -0.08
    may
    -0.08
    men
    -0.08
     may
    -0.07
    869
    -0.07
    ÙĬرا
    -0.07
     sanki
    -0.07
    ampie
    -0.07
    edm
    -0.07
    POSITIVE LOGITS
    hood
    0.07
    veau
    0.07
    -ÑĤаки
    0.07
    Forgery
    0.07
    çİĩ
    0.07
     ought
    0.07
     ÙĬÙĥÙĪÙĨ
    0.07
    ture
    0.06
    .Formatting
    0.06
    tml
    0.06
    Activations Density 0.017%

    No Known Activations