© 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. 129180
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of mechanical or industrial operations

    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
    559
    -0.08
     myself
    -0.07
     rins
    -0.06
     ourselves
    -0.06
     source
    -0.06
    ques
    -0.06
     shovel
    -0.06
     integr
    -0.06
    ource
    -0.06
    cest
    -0.05
    POSITIVE LOGITS
    icity
    0.07
    OKIE
    0.07
    ultz
    0.07
    UNDLE
    0.07
    Ļ¨
    0.07
     Lun
    0.07
    umper
    0.07
     Instruments
    0.06
    ãģ£ãģ¡
    0.06
    áky
    0.06
    Activations Density 0.052%

    No Known Activations