© 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. 15-LLAMASCOPE-RES-131K
    11. 61857
    Prev
    Next
    INDEX
    Explanations

    phrases related to recognition and acknowledgment of contributions and achievements

    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
    ısından
    -0.09
    ibar
    -0.08
    .utf
    -0.07
    vÃŃc
    -0.07
    ERGE
    -0.07
    UTES
    -0.07
    OLVE
    -0.07
    isko
    -0.07
    mal
    -0.07
    uku
    -0.07
    POSITIVE LOGITS
     themselves
    0.08
     alike
    0.06
     their
    0.06
     whom
    0.06
    their
    0.06
     Jer
    0.05
    wr
    0.05
    ibold
    0.05
     us
    0.05
     sl
    0.05
    Activations Density 0.004%

    No Known Activations