© 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. 104896
    Prev
    Next
    INDEX
    Explanations

    references to years of experience or duration of time in professional contexts

    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
    Forever
    -0.07
    hoff
    -0.06
    soon
    -0.06
    lep
    -0.06
    ãĥ£
    -0.06
    OURS
    -0.06
    iente
    -0.06
     forever
    -0.06
    леÑĢ
    -0.06
    λμ
    -0.06
    POSITIVE LOGITS
     annually
    0.07
    urga
    0.07
    uchos
    0.06
     annual
    0.06
     ëħ¹
    0.06
    ylko
    0.06
    okit
    0.06
     exclusively
    0.06
     Since
    0.06
    uye
    0.06
    Activations Density 0.020%

    No Known Activations