© 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. 89397
    Prev
    Next
    INDEX
    Explanations

    references to specific days of events or schedules

    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
     hol
    -0.07
    elm
    -0.06
    arrison
    -0.06
     Hol
    -0.06
    eb
    -0.06
    aminer
    -0.05
    eway
    -0.05
    ameleon
    -0.05
     Kam
    -0.05
     Cam
    -0.05
    POSITIVE LOGITS
    ศ
    0.07
    jours
    0.07
    illac
    0.07
    ÑĨов
    0.07
    .Override
    0.07
     journée
    0.07
    ardin
    0.07
    åķ¦
    0.07
    afort
    0.07
    pecific
    0.07
    Activations Density 0.007%

    No Known Activations