© 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. 84670
    Prev
    Next
    INDEX
    Explanations

    the mention of "Funny or Die" and related comedic content

    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
    urally
    -0.07
    Ïĥι
    -0.07
    ors
    -0.07
    ï¸ı
    -0.07
    urat
    -0.07
    sing
    -0.07
    LEY
    -0.07
    usk
    -0.06
    uss
    -0.06
    ä¼į
    -0.06
    POSITIVE LOGITS
    erals
    0.09
    yyyy
    0.08
    things
    0.07
     enough
    0.07
    tility
    0.07
    óng
    0.07
     things
    0.07
    ertino
    0.07
    tractor
    0.07
    thing
    0.06
    Activations Density 0.005%

    No Known Activations