© 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. 738
    Prev
    Next
    INDEX
    Explanations

    references to Mexican television and historical context

    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
    ettes
    -0.07
    redit
    -0.07
    izr
    -0.06
    ãĥ¼ãĥª
    -0.06
     Ging
    -0.06
    gom
    -0.06
    cies
    -0.06
    RuleContext
    -0.06
     Fallon
    -0.06
     Blizzard
    -0.06
    POSITIVE LOGITS
    cone
    0.07
    OfSize
    0.07
    azar
    0.07
    kening
    0.07
    LEX
    0.07
    oub
    0.07
    anian
    0.06
    wit
    0.06
    //{{
    0.06
    omid
    0.06
    Activations Density 0.001%

    No Known Activations