© 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. 103679
    Prev
    Next
    INDEX
    Explanations

    references to the "Dow" index or related financial metrics

    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
    sand
    -0.08
    vinces
    -0.07
    inges
    -0.07
    že
    -0.07
     fate
    -0.07
    ysis
    -0.07
    bih
    -0.07
    uegos
    -0.07
    nim
    -0.07
    nova
    -0.07
    POSITIVE LOGITS
    ls
    0.09
    adia
    0.08
    gie
    0.07
     Pron
    0.07
    iki
    0.07
    anford
    0.07
    ser
    0.06
    ever
    0.06
    izia
    0.06
    rah
    0.06
    Activations Density 0.034%

    No Known Activations