© 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. 125658
    Prev
    Next
    INDEX
    Explanations

    programming or technical terminology related to variables and functions

    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
    åįĶ
    -0.08
     Appeal
    -0.07
     dét
    -0.07
    bÃŃ
    -0.07
    коÑĢиÑģÑĤ
    -0.07
    LBL
    -0.07
    utow
    -0.07
    bitmap
    -0.07
     heightFor
    -0.07
     @$_
    -0.07
    POSITIVE LOGITS
    otel
    0.06
    ot
    0.06
    ere
    0.06
     Vul
    0.06
    ugh
    0.06
    uhl
    0.06
     Hell
    0.06
    top
    0.05
     precision
    0.05
     React
    0.05
    Activations Density 0.000%

    No Known Activations