© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3819
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or 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
    ioni
    -0.08
    ÑĮко
    -0.08
    gnore
    -0.08
    uraa
    -0.07
    [...,
    -0.07
    ebek
    -0.07
    enin
    -0.07
    emek
    -0.07
    ieves
    -0.07
    ãĤ¯ãĥ©ãĥĸ
    -0.07
    POSITIVE LOGITS
    0
    0.11
     zero
    0.07
     loss
    0.06
    leigh
    0.06
     «
    0.06
    1
    0.06
    2
    0.06
    Û°
    0.06
     (<
    0.06
     Loss
    0.06
    Activations Density 0.007%

    No Known Activations