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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16733
    Prev
    Next
    INDEX
    Explanations

    terms related to anomalies and system performance

    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
    rente
    -0.07
    668
    -0.07
    éĥİ
    -0.07
    uido
    -0.07
     Trou
    -0.06
    ìĩ¼
    -0.06
    uke
    -0.06
    enticator
    -0.06
    ALLY
    -0.06
     Agenda
    -0.06
    POSITIVE LOGITS
    -proof
    0.08
     prevention
    0.07
    edback
    0.07
     situations
    0.07
     detection
    0.07
     situation
    0.07
     Buster
    0.07
     alert
    0.07
    rowable
    0.07
    Ã
    0.06
    Activations Density 0.112%

    No Known Activations