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. 5611
    Prev
    Next
    INDEX
    Explanations

    proper names or specific identifiers related to people or entities

    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
    que
    -0.07
    ANJI
    -0.07
    ãĤ¦ãĥĪ
    -0.07
    pars
    -0.06
    esiz
    -0.06
     metab
    -0.06
    _mE
    -0.06
    _NEAR
    -0.06
    æ´¥
    -0.06
    -entity
    -0.06
    POSITIVE LOGITS
    acht
    0.08
     party
    0.07
    arrass
    0.07
    xBF
    0.07
     Fail
    0.07
    allback
    0.07
    ooth
    0.07
    ise
    0.06
     failure
    0.06
     Party
    0.06
    Activations Density 0.001%

    No Known Activations