© 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. 125389
    Prev
    Next
    INDEX
    Explanations

    instances of negation and phrases indicating absence or rarity

    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
    анка
    -0.06
    ipy
    -0.06
    ias
    -0.06
    oon
    -0.06
    orra
    -0.06
    oga
    -0.05
    esson
    -0.05
    optera
    -0.05
     dit
    -0.05
    anela
    -0.05
    POSITIVE LOGITS
     nÃło
    0.09
     does
    0.08
    üst
    0.07
    HIR
    0.07
    .Restr
    0.07
    ìĶ
    0.07
    .Suppress
    0.07
     ever
    0.07
     (()
    0.07
    SizePolicy
    0.07
    Activations Density 0.005%

    No Known Activations