© 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. 15-LLAMASCOPE-RES-131K
    11. 61778
    Prev
    Next
    INDEX
    Explanations

    colons, indicating lists or items being enumerated

    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
    stal
    -0.08
     ëĦ¤ìĿ´íĬ¸
    -0.07
    ges
    -0.07
    =$('#
    -0.07
    epar
    -0.07
    NOTE
    -0.07
    ONS
    -0.06
    =$("#
    -0.06
     ucwords
    -0.06
    uch
    -0.06
    POSITIVE LOGITS
     there
    0.07
    Ãł
    0.06
    rieg
    0.06
     Given
    0.06
     fortunes
    0.06
    ufreq
    0.06
     it
    0.06
     no
    0.06
    ffects
    0.06
    licated
    0.06
    Activations Density 0.016%

    No Known Activations