© 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. 17-LLAMASCOPE-RES-131K
    11. 57786
    Prev
    Next
    INDEX
    Explanations

    information related to safety and risk, specifically regarding health and medical conditions

    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
     Goodman
    -0.07
    Æ°
    -0.07
    andom
    -0.07
    éĶ¦
    -0.07
     GOODMAN
    -0.07
    oton
    -0.07
    erg
    -0.07
    oten
    -0.07
    ednou
    -0.06
    Ïİ
    -0.06
    POSITIVE LOGITS
     whether
    0.10
     signs
    0.10
     potential
    0.10
    æĺ¯åIJ¦
    0.09
     presence
    0.09
     possible
    0.09
     Signs
    0.08
     æĺ¯åIJ¦
    0.08
     Whether
    0.07
    whether
    0.07
    Activations Density 0.014%

    No Known Activations