© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29744
    Prev
    Next
    INDEX
    Explanations

    references to monetary transactions or financial issues

    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
    aign
    -0.07
    addock
    -0.07
    ìĤ´
    -0.07
    (strpos
    -0.06
    ds
    -0.06
    ัà¸Ļà¸Ļ
    -0.06
     ours
    -0.06
    tty
    -0.06
    oir
    -0.06
    ÏĦÏī
    -0.06
    POSITIVE LOGITS
     device
    0.08
     feat
    0.08
    omit
    0.07
     facility
    0.07
    device
    0.07
     event
    0.07
     suburb
    0.07
    rezent
    0.07
    firm
    0.07
     institute
    0.07
    Activations Density 0.252%

    No Known Activations