© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70637
    Prev
    Next
    INDEX
    Explanations

    terms related to necessity and requirements

    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
    azor
    -0.07
    æ¬
    -0.07
    ugen
    -0.07
    /apt
    -0.07
    than
    -0.06
     grub
    -0.06
    alle
    -0.06
    ãĤ¥
    -0.06
    kir
    -0.06
    rica
    -0.06
    POSITIVE LOGITS
    /request
    0.09
    Charsets
    0.07
    ">//
    0.07
    igu
    0.07
    HeaderCode
    0.07
    ment
    0.07
     Barnett
    0.06
    IIIK
    0.06
    ±Ð¾ÑĤ
    0.06
    iating
    0.06
    Activations Density 0.009%

    No Known Activations