© 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. 56010
    Prev
    Next
    INDEX
    Explanations

    code elements related to conditional statements and highlights within code

    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
    anzi
    -0.06
    altet
    -0.06
     Fra
    -0.06
    ÌĪ
    -0.06
    is
    -0.06
    asting
    -0.05
    icho
    -0.05
    igest
    -0.05
    با
    -0.05
    ÑĮеÑĢ
    -0.05
    POSITIVE LOGITS
    oreach
    0.09
    onis
    0.08
    ãģıãĤĵ
    0.07
    .codes
    0.07
    "default
    0.07
    anio
    0.07
    vap
    0.07
    \OptionsResolver
    0.07
    aal
    0.07
    ransition
    0.07
    Activations Density 0.004%

    No Known Activations