© 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. 93726
    Prev
    Next
    INDEX
    Explanations

    elements related to academic achievements and employment opportunities

    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
    FML
    -0.07
    isphere
    -0.07
    šk
    -0.07
    taÅŁ
    -0.07
     Retirement
    -0.06
    .hu
    -0.06
    fortawesome
    -0.06
    æī¶
    -0.06
    zte
    -0.06
    paginator
    -0.06
    POSITIVE LOGITS
     eventual
    0.07
    gx
    0.06
     experiences
    0.06
    upon
    0.06
     Describe
    0.06
    oran
    0.06
     former
    0.06
    ocker
    0.06
     future
    0.06
     chosen
    0.05
    Activations Density 0.039%

    No Known Activations