© 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. 9-LLAMASCOPE-RES-131K
    11. 95263
    Prev
    Next
    INDEX
    Explanations

    themes of life-threatening situations or extreme stress

    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
     eros
    -0.07
    805
    -0.06
     Giant
    -0.06
    Âł
    -0.05
    illez
    -0.05
    âĢı
    -0.05
    ial
    -0.05
    ãĤ¤ãĥ«
    -0.05
     assembly
    -0.05
     Carp
    -0.05
    POSITIVE LOGITS
    usercontent
    0.08
    uja
    0.08
     qed
    0.07
    strand
    0.07
     доÑĤ
    0.07
    enheim
    0.07
    adows
    0.07
    OLEAN
    0.07
    pth
    0.07
    ÏĦί
    0.07
    Activations Density 0.033%

    No Known Activations