© 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. 119532
    Prev
    Next
    INDEX
    Explanations

    references to historical dates and significant events

    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
    /Gate
    -0.06
    .Formatter
    -0.06
    رÙĪز
    -0.06
    олом
    -0.06
    ISA
    -0.06
    ÙĪغ
    -0.06
    aya
    -0.06
    imuth
    -0.06
    ERM
    -0.06
     Tay
    -0.06
    POSITIVE LOGITS
     after
    0.11
    after
    0.10
     aftermath
    0.09
    -after
    0.09
     AFTER
    0.08
     post
    0.08
    _after
    0.08
    .after
    0.08
     efter
    0.07
    chine
    0.07
    Activations Density 0.060%

    No Known Activations