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. 43688
    Prev
    Next
    INDEX
    Explanations

    references to specific racing events and schedules

    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
    #{@
    -0.06
    Trademark
    -0.06
    ["@
    -0.06
    ATTRIBUTE
    -0.05
     Juda
    -0.05
     January
    -0.05
     GenerationType
    -0.05
    RING
    -0.05
    _DIP
    -0.05
    Protocol
    -0.05
    POSITIVE LOGITS
    tape
    0.12
     tape
    0.11
    NBC
    0.10
     Tape
    0.10
     tapes
    0.10
     Noon
    0.10
     taped
    0.10
     NBC
    0.09
     Coverage
    0.09
     CNBC
    0.09
    Activations Density 0.029%

    No Known Activations