© 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. 3183
    Prev
    Next
    INDEX
    Explanations

    programming language permission types and their associated values

    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
    vasion
    -0.06
    vol
    -0.06
    andel
    -0.06
    üre
    -0.06
    334
    -0.06
    оÑıн
    -0.06
    лаг
    -0.06
     soul
    -0.06
     Vo
    -0.06
    ãĥ«ãĥĪ
    -0.05
    POSITIVE LOGITS
    Å¡ov
    0.07
     addCriterion
    0.07
    amba
    0.07
     ÐŁÐ¾Ñĩ
    0.07
    enheim
    0.07
    gro
    0.06
    åł´åIJĪãģ¯
    0.06
    Gro
    0.06
    :uint
    0.06
    aka
    0.06
    Activations Density 0.007%

    No Known Activations