© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88754
    Prev
    Next
    INDEX
    Explanations

    terms related to order processing and cancellation in a system

    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
    seau
    -0.08
    ISTRY
    -0.08
    одо
    -0.07
    شاء
    -0.07
    mite
    -0.06
    SYNC
    -0.06
     dobr
    -0.06
    ffi
    -0.06
    ÙģÙĪ
    -0.06
     RequestOptions
    -0.06
    POSITIVE LOGITS
     status
    0.12
     state
    0.12
     statuses
    0.10
    çĬ¶æĢģ
    0.10
     states
    0.09
    -state
    0.09
    status
    0.09
     trạng
    0.09
     stages
    0.09
    (status
    0.08
    Activations Density 0.040%

    No Known Activations