© 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. 82653
    Prev
    Next
    INDEX
    Explanations

    aspects of character development and storytelling elements

    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
    oren
    -0.06
    _CLR
    -0.06
     timespec
    -0.06
    urette
    -0.06
    quee
    -0.06
    han
    -0.06
    Æ°á»Ŀng
    -0.06
    ISC
    -0.06
    amera
    -0.06
    .WinForms
    -0.06
    POSITIVE LOGITS
     book
    0.07
     chapters
    0.07
     novel
    0.07
     chapter
    0.07
    prot
    0.07
    loat
    0.07
     Prot
    0.07
     eps
    0.07
     ep
    0.06
    Prot
    0.06
    Activations Density 0.061%

    No Known Activations