© 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. 79232
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting incidents or issues, particularly those involving lost or stolen items

    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
    ¶Į
    -0.06
    oyer
    -0.06
    ailer
    -0.06
     isr
    -0.06
     sj
    -0.06
    ghi
    -0.06
     lesbische
    -0.06
    éļĽ
    -0.06
    antz
    -0.06
    ken
    -0.06
    POSITIVE LOGITS
    ights
    0.07
    ter
    0.07
     signs
    0.06
     ore
    0.06
     Competitive
    0.06
    oli
    0.06
    egas
    0.06
    efa
    0.06
    /xhtml
    0.06
     Maur
    0.06
    Activations Density 0.001%

    No Known Activations