© 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. 71167
    Prev
    Next
    INDEX
    Explanations

    html or markup tags within the text

    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
    baugh
    -0.07
    iefs
    -0.07
    ibel
    -0.07
     smr
    -0.07
    elda
    -0.07
    xbe
    -0.07
    nat
    -0.06
    ilog
    -0.06
    rium
    -0.06
    лÑİд
    -0.06
    POSITIVE LOGITS
    анÑģ
    0.06
     cruise
    0.06
     Pier
    0.06
     Cruise
    0.06
    TextWriter
    0.06
    oll
    0.06
    è¯Ń
    0.06
     tails
    0.06
    ses
    0.06
    é©
    0.05
    Activations Density 0.002%

    No Known Activations