© 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. 75339
    Prev
    Next
    INDEX
    Explanations

    geographic locations and references to specific counties

    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
    ault
    -0.07
    cmath
    -0.07
    PELL
    -0.07
    оÑģÑĤав
    -0.07
    .gridColumn
    -0.06
    거리
    -0.06
    ellt
    -0.06
    shared
    -0.06
    avras
    -0.06
    ayer
    -0.06
    POSITIVE LOGITS
    _Desc
    0.07
     Morgan
    0.07
    ADVERTISEMENT
    0.06
    anta
    0.06
    anca
    0.06
     Madison
    0.06
     advert
    0.06
     Kitt
    0.06
     Trim
    0.06
     caliente
    0.06
    Activations Density 0.061%

    No Known Activations