© 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. 15-LLAMASCOPE-RES-131K
    11. 89975
    Prev
    Next
    INDEX
    Explanations

    references to famous personalities or characters

    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
    ordes
    -0.09
    isÃŃ
    -0.07
     ("
    -0.07
    inan
    -0.07
    ábado
    -0.07
    uctor
    -0.07
    <quote
    -0.07
    å³
    -0.07
     ('
    -0.07
    ramer
    -0.06
    POSITIVE LOGITS
     accent
    0.07
    )
    0.06
    gap
    0.06
    695
    0.06
    fy
    0.06
     pert
    0.06
    bane
    0.06
    ikat
    0.05
    anova
    0.05
    931
    0.05
    Activations Density 0.005%

    No Known Activations