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

    Neuronpedia

    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. 209
    Prev
    Next
    INDEX
    Explanations

    references to appointments and the act of appointing individuals or officers

    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
    wyn
    -0.08
    fak
    -0.07
     à¹Ĩ
    -0.07
    _prov
    -0.07
    aille
    -0.07
    issen
    -0.07
    ought
    -0.07
    ammers
    -0.06
    xes
    -0.06
    ely
    -0.06
    POSITIVE LOGITS
    ment
    0.08
    ments
    0.07
    ended
    0.07
    ioned
    0.07
    åĵģ
    0.07
    ee
    0.07
    itude
    0.07
    endif
    0.06
    ries
    0.06
    ables
    0.06
    Activations Density 0.008%

    No Known Activations