© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129250
    Prev
    Next
    INDEX
    Explanations

    references to sports teams or franchises along with career achievements and statistics

    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
    assi
    -0.07
    ãģĹãģĭ
    -0.07
    á»ķ
    -0.07
    immel
    -0.06
    ĥģ
    -0.06
    мени
    -0.06
    çĪ·
    -0.06
    ató
    -0.06
    urray
    -0.06
     znam
    -0.06
    POSITIVE LOGITS
    ffen
    0.07
    inis
    0.06
    -wide
    0.06
    raft
    0.06
    HeaderValue
    0.06
    -app
    0.06
    bst
    0.06
    wide
    0.06
    pte
    0.06
     Boone
    0.06
    Activations Density 0.005%

    No Known Activations