© 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. 2828
    Prev
    Next
    INDEX
    Explanations

    terms and references related to government entities and legal proceedings

    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
    lew
    -0.07
    anje
    -0.06
    idend
    -0.06
    ledon
    -0.06
    avel
    -0.06
     Geld
    -0.06
    arium
    -0.06
     اÙĦÙĪÙģ
    -0.06
    adian
    -0.06
    elan
    -0.06
    POSITIVE LOGITS
     v
    0.07
    owitz
    0.06
     Equip
    0.06
    âĢij
    0.06
    \Events
    0.06
    QB
    0.06
    RITE
    0.06
     Revolutionary
    0.06
    uros
    0.06
    ikit
    0.06
    Activations Density 0.072%

    No Known Activations