© 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. 84173
    Prev
    Next
    INDEX
    Explanations

    structured sections or divisions within a text

    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
     besten
    -0.07
    naÄį
    -0.07
     ＿
    -0.07
     Inherits
    -0.07
    .cbo
    -0.07
    quent
    -0.07
    inherits
    -0.07
    cts
    -0.07
    ÙĦت
    -0.07
    hev
    -0.06
    POSITIVE LOGITS
     discussion
    0.09
     discusses
    0.09
     again
    0.08
     discussing
    0.08
     topics
    0.08
     miscellaneous
    0.08
     discuss
    0.08
     chapter
    0.08
     dealing
    0.07
    topic
    0.07
    Activations Density 0.009%

    No Known Activations