© 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. 76884
    Prev
    Next
    INDEX
    Explanations

    HTML tags and punctuation elements

    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
    fty
    -0.06
    zcze
    -0.06
    ress
    -0.06
    rosse
    -0.05
    lege
    -0.05
     Pers
    -0.05
     Corner
    -0.05
    æŃ¯
    -0.05
    ede
    -0.05
    hea
    -0.05
    POSITIVE LOGITS
    alars
    0.08
    avigator
    0.07
    kaç
    0.07
    ıi
    0.07
    &&&&
    0.07
    à¹Ģà¸Ķ
    0.07
    dealloc
    0.07
    _<?
    0.06
    istas
    0.06
    اÙĨ
    0.06
    Activations Density 0.020%

    No Known Activations