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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5394
    Prev
    Next
    INDEX
    Explanations

    expressions of pride and acknowledgment within a community

    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
    DECL
    -0.08
    UGH
    -0.07
     Fare
    -0.07
     boo
    -0.06
    reesome
    -0.06
    plat
    -0.06
    _PHP
    -0.06
    .hw
    -0.06
     urg
    -0.06
    seed
    -0.06
    POSITIVE LOGITS
     pride
    0.34
     proud
    0.33
     Pride
    0.29
     Proud
    0.28
     proudly
    0.22
     brag
    0.16
     boast
    0.15
    roud
    0.12
     boasted
    0.12
     stol
    0.12
    Activations Density 0.040%

    No Known Activations