© 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. 82623
    Prev
    Next
    INDEX
    Explanations

    markers related to demographics and societal roles

    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
    VR
    -0.06
    oyal
    -0.06
     Power
    -0.06
    offee
    -0.06
     Adj
    -0.06
     power
    -0.06
    æ´²
    -0.05
    Power
    -0.05
    272
    -0.05
    iped
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    اکÛĮ
    0.08
    ectl
    0.08
    ishi
    0.07
    ese
    0.07
    zed
    0.07
    ombok
    0.07
    alendar
    0.07
     superf
    0.07
    ubu
    0.07
    Activations Density 0.000%

    No Known Activations