© 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 EvalsExportsinterp-engineNEWAPI 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. 86702
    Prev
    Next
    INDEX
    Explanations

    contrasts between perceptions and reality, especially regarding individual feelings and policy fairness

    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
    ÑģÑĥÑĤ
    -0.08
    _via
    -0.07
    ;break
    -0.07
    SystemService
    -0.07
    ,tp
    -0.07
    stoup
    -0.07
     letterSpacing
    -0.07
    èİ«
    -0.07
    Loader
    -0.06
    rick
    -0.06
    POSITIVE LOGITS
     anything
    0.10
     neither
    0.07
     indeed
    0.06
     plenty
    0.06
     NOT
    0.06
    anything
    0.06
     certainly
    0.06
    ä¸įäºĨ
    0.06
     aspect
    0.06
     Anything
    0.06
    Activations Density 0.103%

    No Known Activations