© 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. 77501
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic creation and character development in narratives

    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
    acco
    -0.06
    entic
    -0.06
     Ker
    -0.06
    bor
    -0.06
    val
    -0.05
    Module
    -0.05
    åĭ
    -0.05
    532
    -0.05
    bir
    -0.05
    yn
    -0.05
    POSITIVE LOGITS
     itself
    0.12
    integral
    0.10
     part
    0.10
    Integral
    0.09
     integral
    0.08
     directly
    0.08
     Integral
    0.08
     souÄįástÃŃ
    0.08
     themselves
    0.08
     Ñģамой
    0.07
    Activations Density 0.067%

    No Known Activations