© 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. 126826
    Prev
    Next
    INDEX
    Explanations

    elements related to cultural representation and artistic expression in literature

    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
    oku
    -0.08
    enet
    -0.07
    arrera
    -0.07
     assort
    -0.07
    lopen
    -0.07
     destinationViewController
    -0.07
    cola
    -0.07
    onen
    -0.07
    erez
    -0.07
    ussen
    -0.07
    POSITIVE LOGITS
     ind
    0.07
     underground
    0.06
    uard
    0.06
    orch
    0.06
     tong
    0.06
     differently
    0.06
    oid
    0.06
     modes
    0.06
     critical
    0.05
     Registers
    0.05
    Activations Density 0.016%

    No Known Activations