© 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. 29546
    Prev
    Next
    INDEX
    Explanations

    phrases related to ratings and evaluations

    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
     Concepts
    -0.07
    ubat
    -0.06
     rub
    -0.06
    ubo
    -0.06
    _Api
    -0.06
    ãĥŃãĥ¼
    -0.06
    itis
    -0.06
    flows
    -0.06
    oler
    -0.06
    eci
    -0.06
    POSITIVE LOGITS
    หม
    0.07
    osg
    0.07
    475
    0.07
    lients
    0.07
    ëł
    0.06
     Cry
    0.06
    kın
    0.06
     SaÄŁ
    0.06
     Antar
    0.06
    amation
    0.06
    Activations Density 0.002%

    No Known Activations