© 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. 87321
    Prev
    Next
    INDEX
    Explanations

    the past tense of verbs indicating actions performed or experienced

    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
    ushima
    -0.07
    omor
    -0.06
    ãĥįãĥ«
    -0.06
     bel
    -0.06
    /swagger
    -0.06
     تز
    -0.06
     cub
    -0.06
    eydi
    -0.06
    _OBJC
    -0.06
    оваÑĢи
    -0.06
    POSITIVE LOGITS
     yesterday
    0.11
     recently
    0.11
    recent
    0.10
    Recently
    0.09
     Yesterday
    0.09
    Yesterday
    0.09
     Recently
    0.08
     lately
    0.08
     вÑĩ
    0.07
    æĺ¨
    0.07
    Activations Density 0.305%

    No Known Activations