© 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. 71071
    Prev
    Next
    INDEX
    Explanations

    terminology and references related to medical conditions, specifically neurodegenerative diseases

    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
    SIM
    -0.06
    éĹ
    -0.06
    avic
    -0.06
     Nashville
    -0.06
    nom
    -0.06
    cloth
    -0.06
    .SDK
    -0.06
     flip
    -0.06
    natal
    -0.06
    ego
    -0.06
    POSITIVE LOGITS
     ALS
    0.09
     electric
    0.07
     motor
    0.07
     muscle
    0.07
     muscles
    0.07
     Motor
    0.07
     disease
    0.07
    oter
    0.07
     Duch
    0.06
    å£
    0.06
    Activations Density 0.001%

    No Known Activations