© 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. 15-LLAMASCOPE-RES-131K
    11. 88396
    Prev
    Next
    INDEX
    Explanations

    references to rescue animals and organizations

    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
    elden
    -0.07
    uele
    -0.07
    cean
    -0.06
    537
    -0.06
     Chicken
    -0.06
    ence
    -0.06
     Gy
    -0.06
    udit
    -0.06
    895
    -0.06
    ema
    -0.06
    POSITIVE LOGITS
     training
    0.10
    Training
    0.09
     Training
    0.09
    -training
    0.09
    training
    0.09
     handler
    0.08
     trained
    0.07
     bordel
    0.07
     trainers
    0.07
     TRAIN
    0.07
    Activations Density 0.006%

    No Known Activations