© 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. 87584
    Prev
    Next
    INDEX
    Explanations

    the word "reportedly" and related reporting language

    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
    ãĥ¼ãĥ¬
    -0.07
    ongyang
    -0.07
     sanki
    -0.07
    usa
    -0.07
    ÃĹ↵↵
    -0.07
    ãĥ¼ãĥĨãĤ£
    -0.07
     ведÑĮ
    -0.07
    è·
    -0.07
    amework
    -0.07
    retry
    -0.06
    POSITIVE LOGITS
    LY
    0.07
    ance
    0.07
    ly
    0.07
    ture
    0.07
    ิà¸ŀ
    0.06
    forth
    0.06
    OperationException
    0.06
     (?)
    0.06
    âijł
    0.06
    kie
    0.06
    Activations Density 0.009%

    No Known Activations