Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5730
    Prev
    Next
    INDEX
    Explanations

    expressions related to interpersonal relationships and support dynamics

    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
    sız
    -0.06
    ayi
    -0.06
    ERVER
    -0.06
    egend
    -0.06
    .postMessage
    -0.06
     Same
    -0.06
    endar
    -0.06
    nings
    -0.06
    andi
    -0.06
    ä»Ķ
    -0.06
    POSITIVE LOGITS
     themselves
    0.49
     himself
    0.49
     herself
    0.47
     ourselves
    0.43
     yourself
    0.42
     itself
    0.41
     oneself
    0.39
     Himself
    0.39
     myself
    0.38
     Yourself
    0.38
    Activations Density 0.400%

    No Known Activations