© 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. 76516
    Prev
    Next
    INDEX
    Explanations

    phrases and discussions around race and cultural identity

    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
    eson
    -0.08
    erson
    -0.08
    roz
    -0.07
    essen
    -0.07
    leich
    -0.07
    261
    -0.07
    asil
    -0.07
    etch
    -0.07
    iros
    -0.07
     UsersController
    -0.07
    POSITIVE LOGITS
    /black
    0.08
    led
    0.07
    issant
    0.06
    LED
    0.06
     who
    0.06
    å´İ
    0.06
    /native
    0.06
    /class
    0.06
    PN
    0.05
    877
    0.05
    Activations Density 0.008%

    No Known Activations