© 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. 56134
    Prev
    Next
    INDEX
    Explanations

    expressions of spiritual devotion and calls for unity

    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
    ToPoint
    -0.07
    епÑĤи
    -0.06
    aphrag
    -0.06
    libs
    -0.06
    acha
    -0.06
    iren
    -0.06
     narrowed
    -0.06
    ãĥĥãĥĹ
    -0.05
    ãĥĥãĤ·ãĥ¥
    -0.05
     Ñģказ
    -0.05
    POSITIVE LOGITS
    287
    0.07
    erti
    0.07
    ÅĽ
    0.07
    é¡ĺ
    0.06
     amen
    0.06
    grant
    0.06
     thank
    0.06
    _redirect
    0.06
    lp
    0.06
    illy
    0.06
    Activations Density 0.014%

    No Known Activations