© 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. 77379
    Prev
    Next
    INDEX
    Explanations

    phrases indicating academic qualifications and research focuses

    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
    polator
    -0.08
    DownList
    -0.08
    isphere
    -0.08
    weit
    -0.08
    ÄįenÃŃ
    -0.08
    нÑıв
    -0.07
    بط
    -0.07
    cona
    -0.07
    ajs
    -0.07
    гов
    -0.07
    POSITIVE LOGITS
     late
    0.07
     Late
    0.07
    late
    0.07
    Late
    0.06
     texts
    0.06
     gerne
    0.06
    rane
    0.06
    bcd
    0.06
     reception
    0.06
     trop
    0.05
    Activations Density 0.054%

    No Known Activations