Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76505
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the frequency or repetition of actions and events

    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
    ero
    -0.07
    ryn
    -0.07
    riel
    -0.06
    ilde
    -0.06
    998
    -0.06
    ynthia
    -0.06
    adesh
    -0.06
    aug
    -0.06
    lu
    -0.06
    oras
    -0.06
    POSITIVE LOGITS
    oeff
    0.08
     Wilkinson
    0.06
     prelim
    0.06
     "'
    0.06
    ault
    0.06
    eterangan
    0.06
    DM
    0.06
     WebClient
    0.06
    Argb
    0.06
    ugas
    0.06
    Activations Density 0.015%

    No Known Activations