© 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. 87832
    Prev
    Next
    INDEX
    Explanations

    statistics related to mental health and social interactions

    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
    zı
    -0.08
    omik
    -0.08
     سÙĨÙĪات
    -0.08
     yearly
    -0.08
     Annual
    -0.07
     annual
    -0.07
    üml
    -0.07
    plers
    -0.07
    füh
    -0.07
    Years
    -0.07
    POSITIVE LOGITS
     someone
    0.09
     somewhere
    0.08
     somebody
    0.07
    resh
    0.07
     Someone
    0.07
    eli
    0.06
    someone
    0.06
    Someone
    0.06
     Crawford
    0.06
    fore
    0.06
    Activations Density 0.007%

    No Known Activations