© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 62499
    Prev
    Next
    INDEX
    Explanations

    the phrases "now" and "then" indicating time transitions

    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
    opoulos
    -0.07
    illin
    -0.06
    ibal
    -0.06
    nds
    -0.06
    ucid
    -0.06
    createFrom
    -0.05
    ulos
    -0.05
    ÌĨ
    -0.05
    thalm
    -0.05
    _verbose
    -0.05
    POSITIVE LOGITS
     standpoint
    0.07
     Ùħض
    0.07
    ANA
    0.07
    aul
    0.07
     viewpoint
    0.07
    ë¡ł
    0.06
    orden
    0.06
    ãģ¹ãģį
    0.06
    ighter
    0.06
     perspective
    0.06
    Activations Density 0.002%

    No Known Activations