© 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. 15-LLAMASCOPE-RES-131K
    6. 11
    Prev
    Next
    INDEX
    Explanations

    numerical values or codes related to event details

    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
    ngrx
    -0.07
    >>)
    -0.07
    antar
    -0.07
    spb
    -0.07
    æ·¡
    -0.07
    êm
    -0.07
    .dtp
    -0.07
    sian
    -0.06
    haft
    -0.06
    ault
    -0.06
    POSITIVE LOGITS
     Fritz
    0.06
    ie
    0.06
     ushort
    0.06
    ĺìĿ´
    0.05
    -none
    0.05
     Townsend
    0.05
    .none
    0.05
     polygon
    0.05
     forecast
    0.05
    \/
    0.05
    Activations Density 0.002%

    No Known Activations