© 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. 5-LLAMASCOPE-RES-131K
    11. 126780
    Prev
    Next
    INDEX
    Explanations

    discussions about healing and emotional recovery following trauma

    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
    enden
    -0.07
    ersed
    -0.06
     gross
    -0.06
    gross
    -0.06
     Dane
    -0.06
    urrect
    -0.06
     MainForm
    -0.06
    inkle
    -0.06
     Ses
    -0.06
    ichier
    -0.06
    POSITIVE LOGITS
    asis
    0.07
     ACT
    0.06
    Em
    0.06
    veau
    0.06
    ä½
    0.06
    emat
    0.06
     Barr
    0.06
    _AMD
    0.06
    _AT
    0.06
    pill
    0.06
    Activations Density 0.398%

    No Known Activations