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. 96045
    Prev
    Next
    INDEX
    Explanations

    elements of data structure definitions and related programming syntax

    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
    ŀ
    -0.06
    su
    -0.06
    395
    -0.06
    lashes
    -0.06
    (Void
    -0.06
    sse
    -0.06
    _LOOKUP
    -0.05
     Göz
    -0.05
    SEA
    -0.05
    ndx
    -0.05
    POSITIVE LOGITS
    afone
    0.07
    osi
    0.07
    bon
    0.07
    âng
    0.07
    eso
    0.07
     Vul
    0.07
     Yani
    0.07
     yu
    0.07
    obi
    0.06
    obia
    0.06
    Activations Density 0.040%

    No Known Activations