© 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. 93769
    Prev
    Next
    INDEX
    Explanations

    musical or rhythmic elements related to alarms and warnings

    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
     hugs
    -0.06
    .flink
    -0.06
     плав
    -0.06
    atrix
    -0.06
     Ramirez
    -0.06
     wink
    -0.06
     миÑĢ
    -0.06
     Goth
    -0.05
     transparent
    -0.05
    yr
    -0.05
    POSITIVE LOGITS
     heard
    0.11
     voices
    0.11
     voice
    0.10
     unheard
    0.09
     louder
    0.09
    voices
    0.09
     голоÑģ
    0.09
     Heard
    0.08
    heard
    0.08
    lou
    0.08
    Activations Density 0.038%

    No Known Activations