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. 44033
    Prev
    Next
    INDEX
    Explanations

    references to variables and parameters in 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
    ugas
    -0.07
    ecure
    -0.07
     abolition
    -0.06
    ìĥ
    -0.06
     âĹĦ
    -0.06
    amet
    -0.06
    xa
    -0.06
     gön
    -0.06
    llx
    -0.06
    _RET
    -0.06
    POSITIVE LOGITS
     Defendants
    0.16
     defendants
    0.15
     Defendant
    0.13
     defendant
    0.12
     Plaintiff
    0.11
     Plaint
    0.10
     allegedly
    0.10
     materially
    0.10
     purported
    0.10
     plaintiffs
    0.09
    Activations Density 0.009%

    No Known Activations