© 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. 94970
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditional or situational scenarios

    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
    rection
    -0.06
    ras
    -0.06
    opal
    -0.06
    ows
    -0.06
    bour
    -0.06
    orges
    -0.06
    slides
    -0.06
    sticks
    -0.05
     Adjustment
    -0.05
    bourg
    -0.05
    POSITIVE LOGITS
    oplevel
    0.08
    ehen
    0.08
     Oasis
    0.08
    egral
    0.07
    alance
    0.07
    âb
    0.07
    ë¶
    0.07
    _BACKEND
    0.07
     nghĩ
    0.07
    _relu
    0.07
    Activations Density 0.016%

    No Known Activations