© 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. 87869
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names associated with individual entities or subjects

    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
    ersh
    -0.07
    SSERT
    -0.07
    inki
    -0.06
    ROID
    -0.06
    itate
    -0.06
    cheid
    -0.06
     '_',
    -0.06
    ลà¸Ńà¸ĩ
    -0.06
    еÑģп
    -0.06
    veau
    -0.06
    POSITIVE LOGITS
     Miss
    0.08
     absence
    0.07
    Miss
    0.07
    -exc
    0.07
    accum
    0.07
     sick
    0.07
     missed
    0.07
     Sick
    0.07
     abs
    0.07
     reasons
    0.07
    Activations Density 0.000%

    No Known Activations