© 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. 62448
    Prev
    Next
    INDEX
    Explanations

    positive affirmations and expressions of quality

    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
    olf
    -0.08
    uji
    -0.08
    /source
    -0.07
    anyl
    -0.06
    recht
    -0.06
    ược
    -0.06
    нÑĤ
    -0.06
    ox
    -0.06
    ffa
    -0.06
     Erl
    -0.06
    POSITIVE LOGITS
     way
    0.06
    ãģĿãģ®
    0.06
    owan
    0.06
    åħ¶ä¸Ń
    0.06
    odÃŃ
    0.06
     implications
    0.06
     thereof
    0.06
    ãģİ
    0.06
    hof
    0.06
    avr
    0.06
    Activations Density 0.027%

    No Known Activations