© 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. 126875
    Prev
    Next
    INDEX
    Explanations

    elements of educational and professional credentials

    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
    villa
    -0.07
    Ñıг
    -0.07
    äºĭ
    -0.07
     è¡
    -0.07
    íĬ
    -0.06
    :č↵č↵
    -0.06
    owell
    -0.06
    ãĤ¹ãĤ¿ãĥ¼
    -0.06
     Normally
    -0.06
    .hh
    -0.06
    POSITIVE LOGITS
    unken
    0.07
     May
    0.07
    .scalablytyped
    0.07
    cesso
    0.07
     Lace
    0.06
    ints
    0.06
     unspecified
    0.06
    IClient
    0.06
     addCriterion
    0.06
    ANGLES
    0.06
    Activations Density 0.027%

    No Known Activations