© 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 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. 60980
    Prev
    Next
    INDEX
    Explanations

    quantifiers and adjectives related to quality or extent

    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
    277
    -0.07
    utenberg
    -0.07
    pps
    -0.07
    istik
    -0.07
    ostel
    -0.07
    264
    -0.06
    267
    -0.06
    958
    -0.06
    STS
    -0.06
     bam
    -0.06
    POSITIVE LOGITS
    zee
    0.07
    द
    0.06
    cate
    0.06
    δε
    0.06
     publicity
    0.06
    league
    0.06
    eller
    0.06
    vant
    0.06
    oodle
    0.06
    icient
    0.06
    Activations Density 0.031%

    No Known Activations