© 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. 15-LLAMASCOPE-RES-131K
    11. 87280
    Prev
    Next
    INDEX
    Explanations

    references to travel arrangements and consultations

    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
     é«
    -0.07
    lj
    -0.06
     Strand
    -0.06
    andre
    -0.06
    prox
    -0.06
     Kod
    -0.06
     Dro
    -0.06
    oplevel
    -0.06
    OrCreate
    -0.05
     Kar
    -0.05
    POSITIVE LOGITS
    outu
    0.09
     embell
    0.07
    æĻ¶
    0.07
    ayo
    0.07
    thal
    0.07
    ONGL
    0.07
     какой
    0.07
    egis
    0.07
    additional
    0.07
     Fay
    0.07
    Activations Density 0.159%

    No Known Activations