© 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. 18301
    Prev
    Next
    INDEX
    Explanations

    phrases related to animal use and benefits

    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
    ContentLoaded
    -0.07
    ãĤĤãģĹ
    -0.07
    erte
    -0.07
    ALES
    -0.06
    een
    -0.06
    è¼
    -0.06
    æģµ
    -0.06
    acia
    -0.06
    azzo
    -0.06
    éİ
    -0.06
    POSITIVE LOGITS
     purposes
    0.10
     reasons
    0.07
     consumption
    0.06
     profit
    0.06
    ymi
    0.06
     use
    0.06
     Reasons
    0.06
    ym
    0.06
    /events
    0.06
     sale
    0.06
    Activations Density 0.020%

    No Known Activations