© 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. 28781
    Prev
    Next
    INDEX
    Explanations

    references to the word "Ele" or similar sequences in various contexts

    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
    .scalablytyped
    -0.08
    achten
    -0.07
    ree
    -0.07
    uisse
    -0.06
    apgolly
    -0.06
    омеÑĢ
    -0.06
    omet
    -0.06
    ring
    -0.06
    ret
    -0.06
    moz
    -0.06
    POSITIVE LOGITS
    ardy
    0.07
    uter
    0.07
    angler
    0.07
    лоÑĩ
    0.06
    366
    0.06
    ativity
    0.06
    stown
    0.06
    ãĥ¼ãĥī
    0.06
    urette
    0.06
     dime
    0.06
    Activations Density 0.009%

    No Known Activations