© 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. 103600
    Prev
    Next
    INDEX
    Explanations

    references to specific culture or locale identifiers, such as language codes

    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
     evolution
    -0.06
     spin
    -0.06
    648
    -0.06
    isbury
    -0.06
    eson
    -0.06
    bery
    -0.05
    aepernick
    -0.05
    crast
    -0.05
    veillance
    -0.05
    ippet
    -0.05
    POSITIVE LOGITS
    ارس
    0.08
    åºŃ
    0.07
    ụn
    0.07
    à¹ģà¸ľ
    0.07
    ýt
    0.07
    _MATERIAL
    0.07
    اسÙĩ
    0.07
    atta
    0.07
    ALSE
    0.07
    ï¼ł
    0.07
    Activations Density 0.002%

    No Known Activations