© 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. 17-LLAMASCOPE-RES-131K
    11. 60088
    Prev
    Next
    INDEX
    Explanations

    references to artistic expression and the significance of art in life

    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
    ham
    -0.07
    ark
    -0.06
     shock
    -0.06
     Yourself
    -0.06
    agine
    -0.06
    ug
    -0.06
    anch
    -0.06
    ibir
    -0.06
    ales
    -0.06
    etur
    -0.05
    POSITIVE LOGITS
     part
    0.08
    alnız
    0.08
    itel
    0.07
    chosen
    0.07
     our
    0.07
    yat
    0.07
    Ïĥκε
    0.07
    ÚĺÙĨ
    0.07
    #ac
    0.07
    åįļ士
    0.07
    Activations Density 0.025%

    No Known Activations