© 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. 29082
    Prev
    Next
    INDEX
    Explanations

    time indicators, specifically references to 'am' and 'pm'

    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
    keh
    -0.07
    ients
    -0.07
    aft
    -0.06
     Stam
    -0.06
    VICE
    -0.06
    AWN
    -0.06
    occo
    -0.06
    (Of
    -0.06
    guest
    -0.06
    avana
    -0.06
    POSITIVE LOGITS
    onga
    0.07
    179
    0.07
    _compiler
    0.07
    akening
    0.07
    nger
    0.07
    phasis
    0.07
    ogeneous
    0.07
    ÑĨин
    0.07
    etes
    0.07
    itere
    0.07
    Activations Density 0.006%

    No Known Activations