© 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. 93477
    Prev
    Next
    INDEX
    Explanations

    important dates and numerical information relevant to historical events

    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
    vanished
    -0.07
     Nack
    -0.07
    εÏĦ
    -0.06
     تخصص
    -0.06
     konus
    -0.06
    éIJĺ
    -0.06
     Pols
    -0.06
    staking
    -0.06
    ergus
    -0.06
    xbf
    -0.06
    POSITIVE LOGITS
    imals
    0.08
    irate
    0.07
    ozy
    0.07
    avern
    0.06
    ullet
    0.06
    inox
    0.06
    -fontawesome
    0.06
    -toggler
    0.06
    ilar
    0.06
    solete
    0.06
    Activations Density 0.002%

    No Known Activations