© 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. 95503
    Prev
    Next
    INDEX
    Explanations

    instances of notable achievements or milestones in a narrative context

    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
    aler
    -0.06
    akis
    -0.06
     incoming
    -0.06
     alarak
    -0.06
    halb
    -0.06
    /date
    -0.06
    incoming
    -0.05
     Davidson
    -0.05
    avid
    -0.05
    ossed
    -0.05
    POSITIVE LOGITS
     followed
    0.12
     another
    0.09
    æİ¥çĿĢ
    0.09
    follow
    0.08
     Another
    0.08
    çŁ¢
    0.08
    another
    0.07
     دÛĮگرÛĮ
    0.07
     subsequent
    0.07
    eyin
    0.07
    Activations Density 0.017%

    No Known Activations