© 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 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. 130506
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to medical and anatomical descriptions

    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
     hearts
    -0.06
     intest
    -0.06
    _crc
    -0.06
     heart
    -0.06
    -heart
    -0.06
     abdominal
    -0.06
    å¿ĥ
    -0.06
    èħ¹
    -0.06
    versations
    -0.06
     Heart
    -0.06
    POSITIVE LOGITS
     Mouth
    0.09
    Speech
    0.08
     Speech
    0.08
     Voice
    0.08
     mouth
    0.08
     speech
    0.08
    Voice
    0.07
    speech
    0.07
     Facial
    0.07
     voice
    0.07
    Activations Density 0.009%

    No Known Activations