© 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. 61649
    Prev
    Next
    INDEX
    Explanations

    references to online resources for checking information and services

    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
     Ket
    -0.06
    ugi
    -0.06
    aan
    -0.06
     Fax
    -0.06
     Loy
    -0.06
    iy
    -0.06
    eri
    -0.06
    865
    -0.05
    Ñĩа
    -0.05
     Ven
    -0.05
    POSITIVE LOGITS
     tool
    0.07
    unos
    0.07
    Https
    0.07
    -tool
    0.07
    chner
    0.07
     baiser
    0.07
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.07
    interactive
    0.07
    ¦æĥħ
    0.07
     Tool
    0.06
    Activations Density 0.021%

    No Known Activations