© 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. 28096
    Prev
    Next
    INDEX
    Explanations

    information about pandemic experiences and the impact on personal lives

    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
    aln
    -0.06
     Albert
    -0.06
    udden
    -0.06
    .mvc
    -0.05
    ely
    -0.05
     Dale
    -0.05
    ubu
    -0.05
    ht
    -0.05
    uzzi
    -0.05
    Https
    -0.05
    POSITIVE LOGITS
     normals
    0.08
     ноÑĢм
    0.07
     normalized
    0.07
    _UNICODE
    0.07
     normal
    0.07
    каÑĢ
    0.07
    :normal
    0.06
    ä¹ł
    0.06
    ORITY
    0.06
    -normal
    0.06
    Activations Density 0.022%

    No Known Activations