© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83954
    Prev
    Next
    INDEX
    Explanations

    key figures and their actions related to announcements or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Function words, punctuation marks, and formatting elements that maintain document structure across various technical and formal text types.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ropoda
    -0.07
    ||||
    -0.07
    ercul
    -0.07
    Æł
    -0.06
    .MixedReality
    -0.06
    vanished
    -0.06
    ptime
    -0.06
    Contained
    -0.06
    ÙħÙĪÙĦ
    -0.06
    elp
    -0.06
    POSITIVE LOGITS
    esso
    0.06
    ALI
    0.06
    ÃľR
    0.06
    pek
    0.06
    oha
    0.05
     phen
    0.05
    IRMWARE
    0.05
    usch
    0.05
     à¤
    0.05
    ÏĦεÏģ
    0.05
    Activations Density 3.011%

    No Known Activations