© 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. 9-LLAMASCOPE-RES-131K
    11. 95685
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting related to scientific publications

    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
     Pros
    -0.06
    vic
    -0.06
    iddi
    -0.06
    isko
    -0.06
     Depot
    -0.06
     Drag
    -0.06
    azen
    -0.06
    ori
    -0.06
    iese
    -0.06
    ile
    -0.06
    POSITIVE LOGITS
     eskort
    0.08
     FindObjectOfType
    0.08
    VML
    0.07
    autos
    0.07
    ãĥ¼ãĤ¯
    0.07
    ghi
    0.07
    quo
    0.07
     Pháp
    0.06
    VERR
    0.06
    inos
    0.06
    Activations Density 0.001%

    No Known Activations