© 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. 129237
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or defiance

    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
    alg
    -0.06
    Ĭ
    -0.06
    æīį
    -0.06
    owitz
    -0.06
    ongyang
    -0.06
    akis
    -0.06
     Gee
    -0.06
    ÙħاÙħ
    -0.06
    lio
    -0.06
    edii
    -0.05
    POSITIVE LOGITS
     Screw
    0.11
     screw
    0.10
     heck
    0.09
    iska
    0.08
     hell
    0.08
    forget
    0.08
     forget
    0.07
    Forget
    0.07
    ORN
    0.07
    agnar
    0.07
    Activations Density 0.051%

    No Known Activations