© 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. 190
    Prev
    Next
    INDEX
    Explanations

    expressions of musical enjoyment and appreciation

    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
    785
    -0.07
     nib
    -0.07
     Alb
    -0.06
    atten
    -0.06
    òi
    -0.05
     ill
    -0.05
    xdf
    -0.05
     Enlight
    -0.05
     sho
    -0.05
    ables
    -0.05
    POSITIVE LOGITS
    otime
    0.07
    éģ©çĶ¨
    0.07
    _NOP
    0.07
    ÑģÑĤÑĢа
    0.06
     Gale
    0.06
    ÙĴس
    0.06
    antha
    0.06
    dna
    0.06
    rega
    0.06
    azzo
    0.06
    Activations Density 0.010%

    No Known Activations