© 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. 9-LLAMASCOPE-RES-131K
    11. 95764
    Prev
    Next
    INDEX
    Explanations

    phrases indicating competition and rankings

    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
    LEAN
    -0.08
    á»IJ
    -0.07
     Dise
    -0.07
     VERBOSE
    -0.07
    _WAKE
    -0.06
     sobie
    -0.06
     IRequest
    -0.06
    åĿĤ
    -0.06
    166
    -0.06
    νÏİ
    -0.06
    POSITIVE LOGITS
     between
    0.06
    atter
    0.06
    æģ
    0.06
     patri
    0.06
    pis
    0.06
    yped
    0.06
     Kirst
    0.05
     last
    0.05
     âĶ
    0.05
    odia
    0.05
    Activations Density 0.037%

    No Known Activations