© 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. 94630
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate causation or consequence

    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
     others
    -0.08
    éĤ£
    -0.07
     thats
    -0.07
     its
    -0.07
    éĤ£æł·
    -0.07
     bunun
    -0.07
    its
    -0.07
    ç
    -0.07
     Others
    -0.06
    è¿Ļä¸Ģ
    -0.06
    POSITIVE LOGITS
    /stdc
    0.07
    rz
    0.07
    ãĥ³ãĤ¿
    0.06
    rase
    0.06
    heure
    0.06
    oretical
    0.06
    agos
    0.06
    argas
    0.06
    oret
    0.06
    .usermodel
    0.06
    Activations Density 0.110%

    No Known Activations