© 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. 125590
    Prev
    Next
    INDEX
    Explanations

    references to events and celebrations

    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
    rell
    -0.06
     no
    -0.06
     Formatting
    -0.06
     my
    -0.06
     legacy
    -0.06
    -toggler
    -0.06
     our
    -0.05
     redundant
    -0.05
    bak
    -0.05
    (NS
    -0.05
    POSITIVE LOGITS
     nhằm
    0.08
     aims
    0.08
     sẽ
    0.07
    lain
    0.07
    aims
    0.07
    will
    0.07
    .untracked
    0.07
     hoped
    0.07
     поможеÑĤ
    0.06
    argon
    0.06
    Activations Density 0.027%

    No Known Activations