© 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. 15-LLAMASCOPE-RES-131K
    11. 88187
    Prev
    Next
    INDEX
    Explanations

    PHP variable assignments and method calls

    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
    ÄĽtÅ¡
    -0.08
    à¸Ĥ
    -0.08
    .Mask
    -0.07
    éri
    -0.07
    EMPL
    -0.07
    úi
    -0.07
     pÅĻiÄįemž
    -0.07
    /cms
    -0.07
    lh
    -0.06
    uji
    -0.06
    POSITIVE LOGITS
    soever
    0.07
    aur
    0.07
    iqu
    0.07
    sher
    0.07
    s
    0.06
    etch
    0.06
    idia
    0.06
    nier
    0.06
    embr
    0.06
    Å¡ka
    0.06
    Activations Density 0.006%

    No Known Activations