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. 44059
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and phrases related to coding and programming concepts

    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
     tails
    -0.06
    SetBranch
    -0.06
    anzeigen
    -0.06
    éĿĻ
    -0.06
    WEBPACK
    -0.06
    efs
    -0.06
    Keyword
    -0.06
    ös
    -0.06
    spd
    -0.05
    urls
    -0.05
    POSITIVE LOGITS
    consum
    0.11
     response
    0.10
     consumes
    0.10
    produ
    0.09
     produces
    0.09
     nickname
    0.09
     Consum
    0.09
     Produ
    0.09
     notes
    0.09
     required
    0.08
    Activations Density 0.002%

    No Known Activations