© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95547
    Prev
    Next
    INDEX
    Explanations

    connections or references to prior information or ideas

    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
    prite
    -0.07
    urdu
    -0.07
    azing
    -0.07
    ampton
    -0.07
     вел
    -0.06
    DidLoad
    -0.06
     Animalia
    -0.06
    ondheim
    -0.06
    auge
    -0.06
    358
    -0.06
    POSITIVE LOGITS
    nbsp
    0.07
    ansom
    0.07
     Conj
    0.06
     ìĤ¬íķŃ
    0.06
     yasal
    0.06
     infos
    0.06
    #
    0.06
    quot
    0.06
    _Tis
    0.06
    ramework
    0.06
    Activations Density 0.001%

    No Known Activations