© 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. 127855
    Prev
    Next
    INDEX
    Explanations

    hyphenated words or compounds related to measurements and descriptions

    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
    ategorized
    -0.07
    kil
    -0.06
    iaux
    -0.06
    erap
    -0.06
    áºŃt
    -0.06
    riend
    -0.06
    urgical
    -0.06
    -devel
    -0.06
    kap
    -0.06
    ption
    -0.06
    POSITIVE LOGITS
    ì§ľ
    0.08
     Vic
    0.07
     vic
    0.06
    /Gate
    0.06
    MSN
    0.06
    (Intent
    0.06
    illion
    0.06
    ãĥŃãĥ¼
    0.06
    ope
    0.06
    peat
    0.06
    Activations Density 0.025%

    No Known Activations