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. 22-LLAMASCOPE-RES-131K
    6. 5564
    Prev
    Next
    INDEX
    Explanations

    dates and numerical identifiers related to events

    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
    oot
    -0.07
    rani
    -0.07
    ickle
    -0.06
    aju
    -0.06
    anye
    -0.06
    obo
    -0.06
    ayah
    -0.06
    åĽ½äº§
    -0.06
    ÅĽ
    -0.06
    (es
    -0.06
    POSITIVE LOGITS
    th
    0.08
    ä»Ĭå¹´
    0.08
    STER
    0.07
    Ø«
    0.07
    thin
    0.07
    SSIP
    0.07
    STANCE
    0.07
    ']!='
    0.06
    ATOR
    0.06
    .opend
    0.06
    Activations Density 0.026%

    No Known Activations