© 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 EvalsExportsinterp-engineNEWAPI 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. 61891
    Prev
    Next
    INDEX
    Explanations

    appearances of specific organizations and events

    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
    arn
    -0.07
    OKIE
    -0.07
    èĺ
    -0.07
    CEPTION
    -0.06
    aeda
    -0.06
     scaleFactor
    -0.06
    ÑĨен
    -0.06
    mey
    -0.05
    transfer
    -0.05
    inz
    -0.05
    POSITIVE LOGITS
     hosting
    0.09
     host
    0.09
     hosts
    0.08
    host
    0.08
    -host
    0.08
     invite
    0.07
     Host
    0.07
    .host
    0.07
     invites
    0.07
    Host
    0.07
    Activations Density 0.032%

    No Known Activations