© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82725
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of exploits and vulnerabilities in computer systems

    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
    âb
    -0.07
    ülü
    -0.07
    ạt
    -0.07
    osite
    -0.07
    á»Ļng
    -0.06
    Ñıн
    -0.06
     Bhar
    -0.06
    (ERR
    -0.06
    ayed
    -0.06
    iliz
    -0.06
    POSITIVE LOGITS
    iti
    0.06
     haci
    0.06
     Cunningham
    0.06
     igen
    0.06
    تÙĪØ§ÙĨ
    0.06
    ĭ
    0.06
    (es
    0.06
     endregion
    0.06
    _AT
    0.06
    apgolly
    0.06
    Activations Density 0.016%

    No Known Activations