© 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. 126971
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or scenarios

    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
    برÛĮ
    -0.08
    ìĸ´ëĤĺ
    -0.07
    antor
    -0.07
    ymi
    -0.07
    ITTE
    -0.07
    utsch
    -0.07
     Ø´ÙĨاسÛĮ
    -0.07
    Ø·Ùħ
    -0.07
    dÄĽ
    -0.07
    raig
    -0.07
    POSITIVE LOGITS
     no
    0.10
     none
    0.07
     nothing
    0.07
     nada
    0.06
    ignal
    0.06
    -no
    0.06
     zero
    0.06
    659
    0.06
     Bro
    0.06
     only
    0.06
    Activations Density 0.002%

    No Known Activations