© 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. 70892
    Prev
    Next
    INDEX
    Explanations

    terms related to changes and measurements in physical properties or 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
    mand
    -0.06
    èĸ¦
    -0.06
     Schro
    -0.06
    postalcode
    -0.06
    adier
    -0.06
    alia
    -0.06
     bud
    -0.06
    tool
    -0.06
    thing
    -0.06
     jud
    -0.06
    POSITIVE LOGITS
     fortunes
    0.07
    nict
    0.07
    aniu
    0.07
    iento
    0.06
    ocht
    0.06
     due
    0.06
    azel
    0.06
    igo
    0.06
    ismet
    0.06
    acer
    0.06
    Activations Density 0.072%

    No Known Activations