© 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. 60677
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements or quantities

    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
    ing
    -0.09
    ed
    -0.07
    edla
    -0.06
    lore
    -0.06
    ingham
    -0.06
     Franken
    -0.06
     miêu
    -0.06
    ING
    -0.06
    elize
    -0.06
    ãĥĹãĥ©
    -0.06
    POSITIVE LOGITS
     tw
    0.07
    ynes
    0.06
    venta
    0.06
    ä¸Ģç§į
    0.06
    swers
    0.06
    å¥
    0.06
    owa
    0.06
    ÅĽci
    0.06
    .tm
    0.06
    ulton
    0.06
    Activations Density 0.000%

    No Known Activations