© 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. 57627
    Prev
    Next
    INDEX
    Explanations

    scientific names of organisms in data sets

    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
    /footer
    -0.07
    Setter
    -0.07
    ottom
    -0.07
    ãĤ«ãĥĨãĤ´ãĥª
    -0.07
    IDO
    -0.07
    /react
    -0.07
     fisse
    -0.07
     PoÄįet
    -0.07
    ìĹħ
    -0.07
    ©
    -0.06
    POSITIVE LOGITS
     flight
    0.08
    optera
    0.07
     picnic
    0.06
     ent
    0.06
    icol
    0.06
     Bernstein
    0.06
     зал
    0.06
     Mold
    0.06
     mold
    0.06
     Gst
    0.06
    Activations Density 0.018%

    No Known Activations