Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93749
    Prev
    Next
    INDEX
    Explanations

    phrases that express nullity or insignificance

    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
    uren
    -0.08
    oker
    -0.08
    浦
    -0.06
    ruptcy
    -0.06
    resco
    -0.06
    ома
    -0.06
    بÙĦ
    -0.06
    antan
    -0.06
    epy
    -0.06
    ograd
    -0.06
    POSITIVE LOGITS
     Duis
    0.07
     Laud
    0.07
    asz
    0.07
     Nothing
    0.07
    isis
    0.06
     happens
    0.06
    _FATAL
    0.06
    Nothing
    0.06
     else
    0.06
    kke
    0.06
    Activations Density 0.008%

    No Known Activations