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

    Neuronpedia

    Jacobian LensNEW
    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. 88556
    Prev
    Next
    INDEX
    Explanations

    references to prices or fees associated with services or entry

    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
    udas
    -0.06
     Torrent
    -0.06
    stre
    -0.06
    :
    -0.06
    heiro
    -0.05
    striction
    -0.05
     especially
    -0.05
    FS
    -0.05
    pected
    -0.05
    ENS
    -0.05
    POSITIVE LOGITS
     /*č↵
    0.08
    ilim
    0.08
    amac
    0.07
    humidity
    0.07
    igu
    0.07
    ulumi
    0.07
     DateTimeKind
    0.07
     ÑĪÑĤÑĥ
    0.07
    âĶĢâĶĢâĶĢâĶĢ
    0.07
    amburg
    0.07
    Activations Density 0.013%

    No Known Activations