© 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. 5-LLAMASCOPE-RES-131K
    6. 126954
    Prev
    Next
    INDEX
    Explanations

    comparisons that include the phrase "as X as Y."

    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
    uke
    -0.08
    baugh
    -0.07
    ahkan
    -0.07
    ramer
    -0.06
    .scalablytyped
    -0.06
    าà¸ĩ
    -0.06
    alte
    -0.06
    OMEM
    -0.06
    alis
    -0.06
    erner
    -0.06
    POSITIVE LOGITS
    _hpp
    0.07
    _TER
    0.06
    /from
    0.06
     prost
    0.06
    βι
    0.06
    amd
    0.06
     Cooke
    0.06
    Charsets
    0.06
    usterity
    0.06
     Cary
    0.06
    Activations Density 0.005%

    No Known Activations