Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96064
    Prev
    Next
    INDEX
    Explanations

    structural elements and properties in coding or markup languages

    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
    ÌĨ
    -0.07
    allo
    -0.07
    bum
    -0.07
    reo
    -0.07
    pha
    -0.07
     asm
    -0.07
    .pb
    -0.07
     insp
    -0.07
    mland
    -0.07
    gren
    -0.07
    POSITIVE LOGITS
    aka
    0.07
    DownList
    0.06
    312
    0.06
    316
    0.06
    313
    0.06
    otal
    0.06
    ce
    0.06
     Roe
    0.06
    lad
    0.06
     Ad
    0.05
    Activations Density 0.000%

    No Known Activations