© 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. 40932
    Prev
    Next
    INDEX
    Explanations

    phrases expressing discontent or criticism

    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
    -être
    -0.08
    ร
    -0.07
    aggio
    -0.07
    ched
    -0.07
    mts
    -0.07
    ous
    -0.07
    asi
    -0.07
    uality
    -0.07
    izing
    -0.07
    arians
    -0.07
    POSITIVE LOGITS
    ensively
    0.15
    /on
    0.12
    /down
    0.10
    beat
    0.10
    wards
    0.09
    /off
    0.09
    shoot
    0.09
    /out
    0.08
    spring
    0.08
    site
    0.08
    Activations Density 0.051%

    No Known Activations