© 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. 56226
    Prev
    Next
    INDEX
    Explanations

    elements related to positive experiences or significant highlights in narratives

    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
    202
    -0.08
    exampleModal
    -0.07
    ει
    -0.07
    _https
    -0.07
    ettings
    -0.07
    ึà¸ģ
    -0.07
    =https
    -0.06
    https
    -0.06
    onec
    -0.06
    aaS
    -0.06
    POSITIVE LOGITS
     "[
    0.07
    neath
    0.07
     “[
    0.06
    quin
    0.06
    ajes
    0.06
    423
    0.06
     Ãĥ
    0.06
    oub
    0.06
     '[
    0.06
    å£ģ
    0.06
    Activations Density 0.000%

    No Known Activations