© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94710
    Prev
    Next
    INDEX
    Explanations

    references to rare medical disorders and conditions

    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
    lyph
    -0.09
    rex
    -0.08
    ãĤ¤ãĤº
    -0.08
    URLException
    -0.08
     WaitForSeconds
    -0.08
    illon
    -0.07
    _TestCase
    -0.07
    lore
    -0.07
    toi
    -0.07
    yntaxException
    -0.07
    POSITIVE LOGITS
    á»±a
    0.06
     Christina
    0.05
     Andreas
    0.05
    ấm
    0.05
    eter
    0.05
     Fischer
    0.05
    unik
    0.05
     clock
    0.05
    us
    0.05
     unintention
    0.05
    Activations Density 0.039%

    No Known Activations