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. 43416
    Prev
    Next
    INDEX
    Explanations

    signals of numerical or categorical data presentations

    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
    evi
    -0.07
    idy
    -0.06
    ixin
    -0.06
    äºĮ
    -0.06
    angi
    -0.05
    assi
    -0.05
    zes
    -0.05
    igu
    -0.05
     strom
    -0.05
    igt
    -0.05
    POSITIVE LOGITS
    /stdc
    0.07
    errat
    0.07
     sorter
    0.07
     Voyager
    0.06
    _utc
    0.06
    -su
    0.06
     Communication
    0.06
     suits
    0.06
    еÑĢе
    0.06
    CNT
    0.06
    Activations Density 0.003%

    No Known Activations