© 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. 9-LLAMASCOPE-RES-131K
    11. 95021
    Prev
    Next
    INDEX
    Explanations

    references to characters and their relationships in the narrative

    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
    ůj
    -0.07
    ÑĤен
    -0.07
    led
    -0.07
    Å¡it
    -0.07
    ifes
    -0.07
    ija
    -0.07
    entr
    -0.07
    леменÑĤ
    -0.06
    enson
    -0.06
     dán
    -0.06
    POSITIVE LOGITS
    927
    0.07
    fone
    0.06
    ramer
    0.06
     reckon
    0.06
    dk
    0.06
    pn
    0.06
    онÑĮ
    0.05
    ê°ľ
    0.05
    одав
    0.05
     compromises
    0.05
    Activations Density 0.057%

    No Known Activations