© 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. 15-LLAMASCOPE-RES-131K
    11. 945
    Prev
    Next
    INDEX
    Explanations

    features related to technology and notifications in wearable devices

    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
    OffsetTable
    -0.07
     harsh
    -0.06
     Middleton
    -0.06
    igroup
    -0.06
    zv
    -0.05
     ours
    -0.05
    wel
    -0.05
    uar
    -0.05
     Maxwell
    -0.05
    oodoo
    -0.05
    POSITIVE LOGITS
    ork
    0.07
    inces
    0.07
    orks
    0.07
    bbb
    0.07
    DataContract
    0.07
    ARTH
    0.07
    úp
    0.07
    æ²¢
    0.06
    .googlecode
    0.06
    aptive
    0.06
    Activations Density 0.016%

    No Known Activations