© 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. 70575
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds, particularly involving carbon, hydrogen, and halogens

    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
    çĪ½
    -0.07
    AccessType
    -0.07
    egin
    -0.06
    roje
    -0.06
    fox
    -0.06
     Orig
    -0.06
    oute
    -0.06
    cbc
    -0.06
     Vehicles
    -0.06
    ière
    -0.06
    POSITIVE LOGITS
     mass
    0.10
     Mass
    0.09
    mass
    0.08
     MASS
    0.08
     atom
    0.08
    Mass
    0.08
     massa
    0.08
     atomic
    0.08
    stoff
    0.08
    _mass
    0.07
    Activations Density 0.025%

    No Known Activations