© 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. 76540
    Prev
    Next
    INDEX
    Explanations

    references to animated children's characters and films

    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
    BYTES
    -0.06
    oom
    -0.06
    aoke
    -0.06
    OOM
    -0.06
    lesi
    -0.05
     æ¥
    -0.05
     step
    -0.05
    ri
    -0.05
    429
    -0.05
    ovice
    -0.05
    POSITIVE LOGITS
    Å¡t
    0.09
     sno
    0.09
    unto
    0.07
    .MessageBox
    0.07
    맹
    0.07
    Å¡Å¥
    0.07
    incy
    0.07
    anuts
    0.07
     Sno
    0.07
     synd
    0.07
    Activations Density 0.002%

    No Known Activations