© 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. 103281
    Prev
    Next
    INDEX
    Explanations

    capital letters, likely indicating proper nouns or significant entities

    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
    plevel
    -0.08
    EGIN
    -0.07
    olumn
    -0.07
    erca
    -0.07
    qt
    -0.07
    ska
    -0.07
    phans
    -0.06
    voje
    -0.06
    autical
    -0.06
    tolua
    -0.06
    POSITIVE LOGITS
    adays
    0.13
    odore
    0.10
    sonian
    0.08
    quarters
    0.08
    etheless
    0.08
    URITY
    0.08
    olson
    0.08
    foundland
    0.07
    ÑįÑĤомÑĥ
    0.07
    हल
    0.07
    Activations Density 0.133%

    No Known Activations