© 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. 88819
    Prev
    Next
    INDEX
    Explanations

    references to shock or unsettling imagery

    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
    оки
    -0.09
    ltra
    -0.08
     بÙĨ
    -0.07
    aspers
    -0.07
    âĢŀP
    -0.07
    ãĢĤãĢĤ↵↵
    -0.07
    âĢ¦"↵↵
    -0.07
    oftware
    -0.07
    ddb
    -0.07
    ’ÑĶ
    -0.07
    POSITIVE LOGITS
     hence
    0.07
     but
    0.06
    ł
    0.06
    enk
    0.06
    204
    0.06
     yet
    0.06
    yet
    0.05
    Ãł
    0.05
    ah
    0.05
     It
    0.05
    Activations Density 0.028%

    No Known Activations