© 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. 28136
    Prev
    Next
    INDEX
    Explanations

    instances of characters or objects disappearing from view

    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
    asa
    -0.07
    alic
    -0.07
    arn
    -0.07
    ãĥ©ãĤ¹
    -0.06
     punch
    -0.06
     downright
    -0.06
     lle
    -0.06
    anic
    -0.06
    LETTE
    -0.06
    anny
    -0.06
    POSITIVE LOGITS
     disappearing
    0.11
     disappear
    0.11
     disappeared
    0.09
     disappears
    0.09
     away
    0.09
     leaving
    0.08
     disappearance
    0.08
    åİ»äºĨ
    0.07
     ÑĥÑħод
    0.07
     Away
    0.07
    Activations Density 0.038%

    No Known Activations