© 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. 84061
    Prev
    Next
    INDEX
    Explanations

    terms and references related to institutional affiliations or roles

    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
    ul
    -0.07
    ore
    -0.06
    opi
    -0.06
    o
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
     addCriterion
    -0.06
    ãģ
    -0.06
    оÑģ
    -0.06
    scopic
    -0.06
    wood
    -0.05
    POSITIVE LOGITS
    moid
    0.08
    ëĶĶìĭľ
    0.08
    Ø·ÙĨ
    0.07
    iculos
    0.07
    ĶĦ
    0.07
    ncy
    0.07
     ==============================================================
    0.07
    ãĥ¼ãĥį
    0.07
    ãĤ¿ãĥ¼
    0.07
     Wend
    0.07
    Activations Density 0.108%

    No Known Activations