© 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. 5-LLAMASCOPE-RES-131K
    6. 126679
    Prev
    Next
    INDEX
    Explanations

    terms related to rice and its cooking

    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
    450
    -0.06
    /account
    -0.06
    deck
    -0.05
    unga
    -0.05
    2
    -0.05
     Deck
    -0.05
     Else
    -0.05
    edir
    -0.05
     constr
    -0.05
    elp
    -0.05
    POSITIVE LOGITS
    rych
    0.08
    ires
    0.08
    ERGY
    0.07
     MainAxisAlignment
    0.07
    arella
    0.07
    mainwindow
    0.07
    phia
    0.07
    SWG
    0.07
    TRL
    0.07
    _signed
    0.07
    Activations Density 0.004%

    No Known Activations