© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62567
    Prev
    Next
    INDEX
    Explanations

    versioning information related to software or applications

    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
    IVES
    -0.06
     cgi
    -0.06
    ood
    -0.06
    GRAM
    -0.06
     tens
    -0.06
    968
    -0.06
    agues
    -0.06
    woke
    -0.05
    agner
    -0.05
    meth
    -0.05
    POSITIVE LOGITS
    bish
    0.08
    otime
    0.07
    -UA
    0.07
    ãĥªãĤ«
    0.07
    lexport
    0.07
    erosis
    0.07
    íĨłíĨł
    0.07
    oplayer
    0.07
    isci
    0.07
    ÑĥÑĢÑĥ
    0.07
    Activations Density 0.000%

    No Known Activations