© 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. 106401
    Prev
    Next
    INDEX
    Explanations

    descriptions of challenging tasks and the assistance needed to complete them

    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
    kova
    -0.07
    ayar
    -0.06
    taire
    -0.06
    tail
    -0.06
    cratch
    -0.06
    apia
    -0.06
    ighb
    -0.06
     NSLocalizedString
    -0.06
    emy
    -0.06
    maz
    -0.06
    POSITIVE LOGITS
     Jew
    0.06
    _Reference
    0.06
    mob
    0.06
    InstanceId
    0.06
    ÙĨا
    0.06
    å¦ĩ
    0.06
    ë§Ŀ
    0.06
    erre
    0.06
    qh
    0.06
     recipro
    0.06
    Activations Density 0.006%

    No Known Activations