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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 43404
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used in formatting text or mathematical expressions

    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
    Indented
    -0.08
    subclass
    -0.07
    ROADCAST
    -0.07
    大ä¼ļ
    -0.07
    ICI
    -0.07
    etler
    -0.07
    INE
    -0.07
    isine
    -0.07
    okino
    -0.06
     заÑģÑĤ
    -0.06
    POSITIVE LOGITS
     components
    0.12
     component
    0.12
     resources
    0.12
     res
    0.09
     source
    0.09
    component
    0.09
     resource
    0.09
     sources
    0.09
    components
    0.09
     ingredients
    0.08
    Activations Density 0.002%

    No Known Activations