© 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. 3321
    Prev
    Next
    INDEX
    Explanations

    phrases related to fame and recognition in the entertainment industry

    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
    ading
    -0.07
    inputEmail
    -0.07
     Fres
    -0.07
    orum
    -0.07
    efe
    -0.07
    âm
    -0.06
    umont
    -0.06
    ide
    -0.06
    erie
    -0.06
    ãĥ«ãĥķ
    -0.06
    POSITIVE LOGITS
     became
    0.09
     Overnight
    0.08
     Became
    0.08
     mainstream
    0.07
     household
    0.07
    rame
    0.07
     career
    0.07
    bec
    0.07
    ãĤĪãģĨ
    0.07
     becoming
    0.06
    Activations Density 0.022%

    No Known Activations