© 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 EvalsExportsinterp-engineNEWAPI 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. 95337
    Prev
    Next
    INDEX
    Explanations

    words related to pain or injury, particularly focusing on the term "ache" and its variations

    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
    strup
    -0.07
     Eins
    -0.07
    æĪ
    -0.06
    éĦ
    -0.06
    iffin
    -0.06
    .scalablytyped
    -0.06
    quette
    -0.06
    avigator
    -0.06
     Dmit
    -0.06
    encer
    -0.06
    POSITIVE LOGITS
    ivement
    0.09
    ieved
    0.08
    med
    0.07
    ieves
    0.07
    illes
    0.07
    ieve
    0.07
    YLON
    0.07
    ingly
    0.07
    uate
    0.07
    è¼ī
    0.07
    Activations Density 0.006%

    No Known Activations