© 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. 76818
    Prev
    Next
    INDEX
    Explanations

    phrases related to higher education systems and their challenges

    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
    ricks
    -0.07
     displacement
    -0.06
    alleries
    -0.06
    ester
    -0.06
    Neg
    -0.06
    cott
    -0.06
    iez
    -0.06
    าà¸ĩ
    -0.06
     curl
    -0.06
     Bewert
    -0.06
    POSITIVE LOGITS
    ibling
    0.07
     CrossRef
    0.07
     addCriterion
    0.07
    _tokenize
    0.06
    inea
    0.06
    INGLE
    0.06
    oner
    0.06
    /single
    0.06
    chia
    0.06
    ãģ¡ãģ¯
    0.06
    Activations Density 0.055%

    No Known Activations