Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5211
    Prev
    Next
    INDEX
    Explanations

    medical terminology and references to experimental procedures related to a specific condition

    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
     dip
    -0.06
     Lo
    -0.05
    .insertBefore
    -0.05
     
    -0.05
     blending
    -0.05
     infiltr
    -0.05
     dips
    -0.05
     trunk
    -0.05
     industrial
    -0.05
     breasts
    -0.05
    POSITIVE LOGITS
     Coch
    0.08
     vestib
    0.08
    abyrinth
    0.08
    YRO
    0.08
     coch
    0.07
    ighb
    0.07
     scala
    0.07
    ìľ¨
    0.07
    Fluid
    0.07
    ikh
    0.07
    Activations Density 0.005%

    No Known Activations