© 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. 71608
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to crisis support and resources for individuals in need

    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
     Parkinson
    -0.07
    liable
    -0.06
    ãģ¤
    -0.06
    ayo
    -0.06
    heim
    -0.06
     fell
    -0.06
    Charset
    -0.06
    ç³ĸ
    -0.06
    .eof
    -0.06
    tro
    -0.05
    POSITIVE LOGITS
     neutral
    0.07
     Integral
    0.07
    æ¢
    0.07
    æģ¨
    0.06
    oldemort
    0.06
    sburg
    0.06
    772
    0.06
     Sabha
    0.06
    emiz
    0.06
    ola
    0.06
    Activations Density 0.004%

    No Known Activations