© 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. 119662
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or assessment in various contexts

    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
    remen
    -0.08
     Ñĥмов
    -0.07
     dane
    -0.07
     sami
    -0.07
    .fig
    -0.07
    ắt
    -0.07
    ÎŃν
    -0.07
    ãĥ³ãĤ¸
    -0.07
    _DEFINITION
    -0.07
    avanaugh
    -0.07
    POSITIVE LOGITS
     likelihood
    0.07
     possible
    0.07
     possibility
    0.06
     approach
    0.06
     need
    0.06
     potential
    0.06
     overall
    0.06
    irth
    0.06
     greater
    0.06
     importance
    0.06
    Activations Density 0.042%

    No Known Activations