© 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. 61548
    Prev
    Next
    INDEX
    Explanations

    descriptions of visual aesthetics and appreciation of color in designs

    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
    criptor
    -0.07
     ÎķÏĢ
    -0.06
     contradict
    -0.06
    ãĥ³ãĥĨãĤ£
    -0.06
    bbe
    -0.06
    ifi
    -0.06
    аÑĤки
    -0.05
    odom
    -0.05
    .snp
    -0.05
    ê´Ģ
    -0.05
    POSITIVE LOGITS
    imson
    0.08
    922
    0.08
     outcome
    0.08
     finished
    0.08
     resultado
    0.07
     final
    0.07
     resulted
    0.07
     výsled
    0.07
     result
    0.07
     RESULT
    0.07
    Activations Density 0.025%

    No Known Activations