© 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. 17-LLAMASCOPE-RES-131K
    11. 125243
    Prev
    Next
    INDEX
    Explanations

    terminologies associated with design, concepts, or classifications

    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
    ridor
    -0.07
    inch
    -0.07
    ÄĻż
    -0.07
    ilib
    -0.07
    aldi
    -0.07
    alc
    -0.06
    ÏĦ
    -0.06
    ember
    -0.06
    ardu
    -0.06
    uge
    -0.06
    POSITIVE LOGITS
    ãĥ§
    0.07
    anness
    0.06
    eview
    0.06
    Ùĩ
    0.06
     Prince
    0.06
    ambil
    0.06
    andid
    0.06
    ÑĪев
    0.06
     amb
    0.06
    wise
    0.05
    Activations Density 0.002%

    No Known Activations