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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18338
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe experiences or qualities with strong emotional or sensory connotations

    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
    uzzi
    -0.07
    	and
    -0.07
     and
    -0.07
     és
    -0.07
    लत
    -0.06
    ê±°ëĤĺ
    -0.06
    czy
    -0.06
    unas
    -0.06
     zwar
    -0.06
    mere
    -0.06
    POSITIVE LOGITS
     alike
    0.07
    ewis
    0.07
    kea
    0.07
     serta
    0.07
     respectively
    0.07
    icha
    0.07
    ÑĤÑĮ
    0.07
    gf
    0.07
    ly
    0.07
    ÃŁer
    0.07
    Activations Density 0.051%

    No Known Activations