© 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. 14562
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate unexpected or unusual outcomes

    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
    unde
    -0.08
    umes
    -0.08
    ¿ÃĤ
    -0.07
    Ñĩи
    -0.07
    _unused
    -0.06
    bright
    -0.06
    unden
    -0.06
    ษ
    -0.06
    grad
    -0.06
    IRM
    -0.06
    POSITIVE LOGITS
    Impossible
    0.16
     impossible
    0.15
     Impossible
    0.15
     imposs
    0.13
     possible
    0.10
    possible
    0.10
     possibility
    0.09
     Possible
    0.09
    Possible
    0.09
     possÃŃvel
    0.09
    Activations Density 0.041%

    No Known Activations