© 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. 88439
    Prev
    Next
    INDEX
    Explanations

    references to reports or observational data, particularly those mentioning authorities or official sources

    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
    tec
    -0.07
    ÑĢоÑĦ
    -0.07
    æĴŃ
    -0.06
     Congress
    -0.06
    mue
    -0.06
    à¸Ĭาà¸ķ
    -0.06
    еÑĢе
    -0.06
    ollectors
    -0.06
    927
    -0.06
    ãĥķãĥĪ
    -0.06
    POSITIVE LOGITS
     reports
    0.08
    kest
    0.07
    inke
    0.07
     latest
    0.07
     recent
    0.07
    anco
    0.06
     local
    0.06
    oslav
    0.06
     Idle
    0.06
     cod
    0.06
    Activations Density 0.014%

    No Known Activations