© 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. 93786
    Prev
    Next
    INDEX
    Explanations

    references to donations and financial support for community programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical identifiers, variable names, and parameters appearing in programming code, mathematical notation, or technical documentation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     [âĢ¦]↵
    -0.07
    IOD
    -0.07
    ÑģÑĤоÑı
    -0.06
    ..↵
    -0.06
    [email
    -0.06
    beb
    -0.06
    CEF
    -0.06
    afc
    -0.06
     âĢ¦↵
    -0.06
    ÙĢÙĢÙĢÙĢ
    -0.06
    POSITIVE LOGITS
    .appspot
    0.10
     пÑĢоÑĦеÑģÑģионалÑĮ
    0.10
     ÑĦедеÑĢалÑĮ
    0.09
    @gmail
    0.09
    using
    0.09
    ienza
    0.08
     ÑĦÑĥнда
    0.08
    галÑĸ
    0.08
     TMPro
    0.08
    eldorf
    0.08
    Activations Density 5.971%

    No Known Activations