© 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. 62098
    Prev
    Next
    INDEX
    Explanations

    identifiers or categories related to design ideas

    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
    ieee
    -0.07
     Ekon
    -0.07
     EÅŁ
    -0.07
    ãĥ³ãĥķ
    -0.07
     enter
    -0.06
    γη
    -0.06
    OTES
    -0.06
    θλη
    -0.06
    unts
    -0.06
     ØŃÚ©
    -0.06
    POSITIVE LOGITS
    ibu
    0.07
    Ĥæķ°
    0.06
    ido
    0.06
    asca
    0.06
    ify
    0.06
    豪
    0.06
    olph
    0.06
    mav
    0.06
    INCT
    0.06
    NCY
    0.06
    Activations Density 0.000%

    No Known Activations