© 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. 87735
    Prev
    Next
    INDEX
    Explanations

    time-related information and timestamps

    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
    oten
    -0.06
     radi
    -0.06
     se
    -0.06
    )((((
    -0.06
    igt
    -0.06
    ÑŁ
    -0.06
    jerne
    -0.06
     seg
    -0.06
    iddy
    -0.05
    _
    -0.05
    POSITIVE LOGITS
    strcasecmp
    0.07
    Äįin
    0.07
    âĢ¢↵↵
    0.07
    ara
    0.07
     Ñĥли
    0.07
    à¹Ĥà¸ŀ
    0.07
     tròn
    0.07
     اÙĦعرب
    0.07
    ÙħÙĪد
    0.07
    .selenium
    0.07
    Activations Density 0.001%

    No Known Activations