© 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. 61089
    Prev
    Next
    INDEX
    Explanations

    names of people and entities mentioned within the text

    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
    ichen
    -0.07
    venue
    -0.07
     Freund
    -0.06
    оÑĩно
    -0.06
    Presence
    -0.06
    -addon
    -0.06
    idon
    -0.06
    elyn
    -0.06
    HASH
    -0.06
    inya
    -0.06
    POSITIVE LOGITS
     family
    0.10
    rs
    0.07
    owie
    0.07
     household
    0.07
    æ°ı
    0.07
    们
    0.07
    ss
    0.07
    ÂŃn
    0.07
    -family
    0.07
     Family
    0.07
    Activations Density 0.008%

    No Known Activations