© 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. 55756
    Prev
    Next
    INDEX
    Explanations

    patterns or identifiers related to degree or level of education

    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
    ivet
    -0.07
    ¶Į
    -0.07
    isle
    -0.06
    etta
    -0.06
     âĹĦ
    -0.06
    erver
    -0.06
    ÙĬرة
    -0.06
    οÏį
    -0.06
    mith
    -0.06
    ides
    -0.06
    POSITIVE LOGITS
    roids
    0.08
    egov
    0.07
    untas
    0.06
    cem
    0.06
    roid
    0.06
    iae
    0.06
    uden
    0.06
    prep
    0.06
    uae
    0.06
    .fil
    0.06
    Activations Density 0.001%

    No Known Activations