© 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. 15-LLAMASCOPE-RES-131K
    11. 27031
    Prev
    Next
    INDEX
    Explanations

    references to training programs and educational courses

    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
    uez
    -0.07
    auf
    -0.07
    inos
    -0.07
    oko
    -0.07
    otyp
    -0.06
    ÑıÑĩ
    -0.06
    chio
    -0.06
    ikal
    -0.06
    egl
    -0.06
    achen
    -0.06
    POSITIVE LOGITS
    train
    0.08
     train
    0.08
    WithPath
    0.07
     training
    0.07
    ifetime
    0.06
    icl
    0.06
    -training
    0.06
    åĵ¡
    0.06
    arer
    0.06
     skill
    0.06
    Activations Density 0.097%

    No Known Activations