© 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. 128634
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of "never" or expressions of absence and negation

    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
    .heroku
    -0.09
    umas
    -0.08
    ลาà¸Ķ
    -0.08
    utches
    -0.07
     æ¤
    -0.07
    kick
    -0.07
    enaire
    -0.07
    .reporting
    -0.07
    ãĤĤãģ£ãģ¨
    -0.07
     æ½
    -0.07
    POSITIVE LOGITS
    ending
    0.08
    -ending
    0.07
    theless
    0.07
     completely
    0.07
     ending
    0.07
     truly
    0.06
    ording
    0.06
    Ending
    0.06
     ex
    0.06
     complete
    0.06
    Activations Density 0.020%

    No Known Activations