© 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. 78754
    Prev
    Next
    INDEX
    Explanations

    terms related to translations and copyright information

    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
    æĮĻ
    -0.06
    kins
    -0.06
    bart
    -0.06
    zá
    -0.06
    closure
    -0.06
     Armed
    -0.06
     renew
    -0.06
    inn
    -0.05
    amina
    -0.05
    olph
    -0.05
    POSITIVE LOGITS
     translators
    0.10
     translator
    0.10
     translation
    0.09
    translator
    0.08
     transl
    0.08
     translated
    0.08
    ç¿»
    0.08
    訳
    0.08
    _translate
    0.08
     ë²Ī
    0.08
    Activations Density 0.013%

    No Known Activations