© 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 EvalsExportsinterp-engineNEWAPI 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. 117740
    Prev
    Next
    INDEX
    Explanations

    conditional statements or checks in programming code that involve numerical comparisons

    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
    ersen
    -0.07
    лаÑĪ
    -0.07
    reh
    -0.07
    ãĥ«ãĥķ
    -0.07
    cplusplus
    -0.07
    isma
    -0.06
    ango
    -0.06
    inh
    -0.06
    holder
    -0.06
    irim
    -0.06
    POSITIVE LOGITS
    0
    0.07
    ropa
    0.06
    oucher
    0.06
    anova
    0.06
    cha
    0.06
    ificate
    0.06
    ãĥ³ãĤ¸
    0.06
    ابر
    0.06
    enance
    0.06
    rop
    0.06
    Activations Density 0.026%

    No Known Activations