© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106566
    Prev
    Next
    INDEX
    Explanations

    statistical data and percentages in the text

    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
    /feed
    -0.07
    etc
    -0.07
     ettir
    -0.07
    ÎķÎļ
    -0.06
    cba
    -0.06
    ÂĿ
    -0.06
    кин
    -0.06
     stuff
    -0.06
    eed
    -0.06
    state
    -0.06
    POSITIVE LOGITS
    longleftrightarrow
    0.07
    usz
    0.07
    nost
    0.06
    istrovstvÃŃ
    0.06
    strup
    0.06
    sko
    0.06
    Occurred
    0.06
    rop
    0.06
    icles
    0.06
    compareTo
    0.06
    Activations Density 0.030%

    No Known Activations