© 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. 77441
    Prev
    Next
    INDEX
    Explanations

    phrases related to disbelief or skepticism

    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
    lyn
    -0.07
     Crowley
    -0.07
    .ly
    -0.07
    amm
    -0.07
     Cour
    -0.06
     yyn
    -0.06
    ortal
    -0.06
    ORIA
    -0.06
    Cour
    -0.06
    aac
    -0.06
    POSITIVE LOGITS
     rolling
    0.07
     mari
    0.06
     Rolling
    0.06
    rog
    0.06
    ikers
    0.06
    vro
    0.06
    алÑĸ
    0.06
    rollable
    0.06
    ÑĢаг
    0.06
    rente
    0.06
    Activations Density 0.052%

    No Known Activations