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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118646
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports rankings and playoff qualifications

    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
     Barrier
    -0.08
    rán
    -0.07
    obb
    -0.07
    ÅĻiv
    -0.06
    PK
    -0.06
    Barrier
    -0.06
    Compat
    -0.06
    ÅĻÃŃm
    -0.06
     barrier
    -0.06
    mage
    -0.06
    POSITIVE LOGITS
    kov
    0.07
    .heroku
    0.07
    slice
    0.07
     slice
    0.07
    cona
    0.07
    anzi
    0.06
     sec
    0.06
    _REMOTE
    0.06
    contro
    0.06
    ίοÏħ
    0.06
    Activations Density 0.007%

    No Known Activations