© 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. 78889
    Prev
    Next
    INDEX
    Explanations

    key components and markets related to industrial materials and technology

    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
    lich
    -0.08
    igar
    -0.07
    asaki
    -0.06
     extrav
    -0.06
     cla
    -0.06
     Redistributions
    -0.06
     Haz
    -0.06
     Mong
    -0.06
    ivery
    -0.05
    uco
    -0.05
    POSITIVE LOGITS
    ì§ij
    0.07
    ombat
    0.07
    åħĥ
    0.07
    å¤ĩ
    0.06
    kre
    0.06
    žený
    0.06
     indispensable
    0.06
    _ALT
    0.06
    consistent
    0.06
     industries
    0.06
    Activations Density 0.011%

    No Known Activations