© 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. 77491
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'finding' or discovery

    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
    maxLength
    -0.07
    ased
    -0.07
     addCriterion
    -0.06
    staking
    -0.06
    tempts
    -0.06
     medi
    -0.06
    ee
    -0.06
    ãĥ¼ãĥ³
    -0.06
     revision
    -0.06
    att
    -0.06
    POSITIVE LOGITS
    ry
    0.08
    amental
    0.07
    ress
    0.07
    RY
    0.07
    lings
    0.07
    /Foundation
    0.07
    ries
    0.07
     Dudley
    0.07
    zik
    0.07
     previews
    0.07
    Activations Density 0.007%

    No Known Activations