© 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 EvalsExportsinterp-engineNEWAPI 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. 120739
    Prev
    Next
    INDEX
    Explanations

    phrases indicating curiosity or analysis in research contexts

    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
    Ñģим
    -0.07
    ibraltar
    -0.07
    ueva
    -0.07
    ylon
    -0.07
    ota
    -0.07
    onec
    -0.07
    첨ë¶Ģ
    -0.07
     AFC
    -0.06
    oret
    -0.06
    jax
    -0.06
    POSITIVE LOGITS
     overall
    0.07
    èª
    0.07
     usage
    0.06
    éł
    0.06
     absolute
    0.06
     votes
    0.06
     اÙĦØ£Ùĥ
    0.06
    usage
    0.06
    igram
    0.06
    /ws
    0.06
    Activations Density 0.000%

    No Known Activations