© 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. 82650
    Prev
    Next
    INDEX
    Explanations

    phrases related to program evaluation and recommendations for improvement

    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
    anke
    -0.06
    alim
    -0.06
    redict
    -0.06
    onium
    -0.06
     Erotik
    -0.06
    AINS
    -0.06
    лоÑģÑĮ
    -0.06
    ÙĪئ
    -0.06
    erken
    -0.06
    imdi
    -0.06
    POSITIVE LOGITS
     annual
    0.08
     fro
    0.07
     whenever
    0.07
    enever
    0.07
     proposed
    0.07
     proposals
    0.07
     trends
    0.07
     any
    0.07
     proposal
    0.07
     Lar
    0.06
    Activations Density 0.007%

    No Known Activations