© 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. 16227
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags

    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
    eldon
    -0.08
    heimer
    -0.07
    cedure
    -0.07
    ikut
    -0.07
    ceptor
    -0.07
    agonal
    -0.07
    illery
    -0.07
    leyici
    -0.07
    atrix
    -0.07
    umann
    -0.07
    POSITIVE LOGITS
    بس
    0.07
    å½±
    0.06
    enu
    0.06
    tl
    0.06
    ,'#
    0.06
    rea
    0.06
    -scripts
    0.06
    .title
    0.06
     title
    0.06
     Howell
    0.06
    Activations Density 0.003%

    No Known Activations