© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 88600
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opinions or sentiments about cultural figures

    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
    ë¶
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
     ARC
    -0.06
    ACE
    -0.06
    ieg
    -0.06
    aft
    -0.06
    ahun
    -0.06
    ivated
    -0.06
    95
    -0.06
    ÑĢÑĥн
    -0.05
    POSITIVE LOGITS
    bast
    0.08
     McB
    0.07
    PLOY
    0.07
     approving
    0.07
     approvals
    0.07
     approve
    0.07
     alive
    0.07
     approval
    0.07
     ghost
    0.06
    iral
    0.06
    Activations Density 0.023%

    No Known Activations