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. 44035
    Prev
    Next
    INDEX
    Explanations

    coding and programming terminology related to memory management

    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
     âĢİ
    -0.06
     mou
    -0.06
     Boutique
    -0.06
    retty
    -0.06
    inks
    -0.06
     ends
    -0.05
    avery
    -0.05
    âĢİ
    -0.05
     Ends
    -0.05
    _fds
    -0.05
    POSITIVE LOGITS
     Workspace
    0.10
    Workspace
    0.10
     workspace
    0.10
    lda
    0.10
     lda
    0.09
     ALPHA
    0.09
     diag
    0.09
     bidi
    0.09
    workspace
    0.08
     storage
    0.08
    Activations Density 0.012%

    No Known Activations