© 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. 54205
    Prev
    Next
    INDEX
    Explanations

    events and announcements related to cancellations and scheduling changes

    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
    çĿ
    -0.07
    ilder
    -0.06
    аг
    -0.06
    reopen
    -0.06
    enna
    -0.06
     taxa
    -0.06
    ÑĦÑĸк
    -0.06
    ophy
    -0.06
     reconnect
    -0.06
     lul
    -0.06
    POSITIVE LOGITS
     cancellation
    0.15
     cancell
    0.15
     cancel
    0.15
     Cancel
    0.14
    Cancel
    0.13
    .cancel
    0.13
    cancel
    0.13
     canc
    0.12
    -cancel
    0.12
     canceled
    0.12
    Activations Density 0.139%

    No Known Activations