© 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. 107459
    Prev
    Next
    INDEX
    Explanations

    mentions of purchasing and distribution activities

    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
    uzzi
    -0.07
    acco
    -0.07
     è¦
    -0.06
    _DEPRECATED
    -0.06
    illion
    -0.06
     ç´
    -0.06
    ίÏĥ
    -0.06
    tent
    -0.06
    chwitz
    -0.06
    gne
    -0.06
    POSITIVE LOGITS
     profit
    0.09
     prof
    0.07
     arbit
    0.07
    ivals
    0.07
    wert
    0.07
     sell
    0.07
    .esp
    0.07
    _markup
    0.07
    çĦ¶åIJİ
    0.06
     PROF
    0.06
    Activations Density 0.021%

    No Known Activations