© 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. 88454
    Prev
    Next
    INDEX
    Explanations

    phrases related to themes of repetition or accumulation

    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
     even
    -0.06
    antt
    -0.06
     Nelson
    -0.06
    _VC
    -0.06
    isters
    -0.06
    .mit
    -0.05
    upt
    -0.05
     also
    -0.05
     TNT
    -0.05
     dokonce
    -0.05
    POSITIVE LOGITS
    utow
    0.08
    Ñħо
    0.07
    uco
    0.07
    wald
    0.07
    ä¹ĭä¸Ģ
    0.07
    emann
    0.07
    layan
    0.07
    Powered
    0.07
    eken
    0.07
    iros
    0.07
    Activations Density 0.023%

    No Known Activations