© 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. 73263
    Prev
    Next
    INDEX
    Explanations

    features and qualities of headphones

    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
     itself
    -0.10
     its
    -0.07
    inder
    -0.07
     alike
    -0.07
     synd
    -0.06
    ÏģαÏĤ
    -0.06
    ç¼
    -0.06
     respectively
    -0.06
    905
    -0.06
    .BLL
    -0.06
    POSITIVE LOGITS
     themselves
    0.12
     thems
    0.08
    imos
    0.07
    gies
    0.07
     FEATURE
    0.07
    eyse
    0.07
     коÑĤоÑĢÑĭе
    0.07
     Welch
    0.06
     weren
    0.06
    —they
    0.06
    Activations Density 0.022%

    No Known Activations