© 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. 17802
    Prev
    Next
    INDEX
    Explanations

    references to institutional accreditation

    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
    undai
    -0.06
    kas
    -0.06
    ereum
    -0.06
    jam
    -0.06
    ÑģÑĤÑĢÑĥ
    -0.06
    empo
    -0.06
    lamaz
    -0.05
    unda
    -0.05
    abil
    -0.05
    wan
    -0.05
    POSITIVE LOGITS
     accred
    0.07
     anale
    0.07
    ANJI
    0.07
     stoi
    0.07
     char
    0.07
     Drama
    0.06
    .quality
    0.06
    pez
    0.06
    ember
    0.06
    asca
    0.06
    Activations Density 0.004%

    No Known Activations