© 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. 58750
    Prev
    Next
    INDEX
    Explanations

    references to conflict or disputes involving authority figures and individual rights

    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
    ÑģÑĤеÑĢ
    -0.08
    ÑĥмÑĥ
    -0.08
    ?type
    -0.07
    ester
    -0.07
    罪
    -0.06
    ÃĸL
    -0.06
     æ®
    -0.06
    urette
    -0.06
    reck
    -0.06
    (Of
    -0.06
    POSITIVE LOGITS
     school
    0.07
    utzer
    0.07
     ult
    0.06
    isme
    0.06
    olicy
    0.06
     singled
    0.06
     Frederick
    0.05
     parental
    0.05
    chen
    0.05
    vi
    0.05
    Activations Density 0.006%

    No Known Activations