© 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. 71135
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code elements related to stylesheets

    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
    edi
    -0.06
    edic
    -0.06
    ymm
    -0.06
    chair
    -0.06
    ahn
    -0.06
    utas
    -0.06
    mith
    -0.06
    excel
    -0.06
    rosis
    -0.06
    æĪĴ
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
    DirectoryName
    0.07
     optarg
    0.07
    ÅĤug
    0.07
    .googleapis
    0.07
    ?family
    0.06
    ser
    0.06
     Jarvis
    0.06
    LBL
    0.06
    uetype
    0.06
    Activations Density 0.001%

    No Known Activations