© 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. 61695
    Prev
    Next
    INDEX
    Explanations

    negative descriptors relating to performance, quality, and ethical concerns

    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
    lek
    -0.08
    ISMATCH
    -0.07
    plex
    -0.07
    atrix
    -0.07
    Ậ
    -0.07
    ijd
    -0.07
    atorio
    -0.07
    erdale
    -0.07
    owie
    -0.07
    çī
    -0.07
    POSITIVE LOGITS
    /un
    0.08
     due
    0.08
    /out
    0.07
    avel
    0.07
    due
    0.07
    /problem
    0.06
    æİī
    0.06
     Due
    0.06
    ment
    0.06
    ments
    0.06
    Activations Density 0.072%

    No Known Activations