© 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. 705
    Prev
    Next
    INDEX
    Explanations

    references to specific episodes and seasons in a series

    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
    éľŀ
    -0.07
    .Magenta
    -0.07
    lish
    -0.07
    FINE
    -0.06
    lasses
    -0.06
     zbo
    -0.06
    itz
    -0.06
    362
    -0.06
    isc
    -0.06
    -aut
    -0.06
    POSITIVE LOGITS
    uyo
    0.07
    itta
    0.07
    unya
    0.06
     Fors
    0.06
    пов
    0.06
    Callable
    0.06
    -Series
    0.06
    ÄĽk
    0.06
    VERTISE
    0.06
    owski
    0.06
    Activations Density 0.028%

    No Known Activations