© 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. 124085
    Prev
    Next
    INDEX
    Explanations

    references to education systems and programs

    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
    ambre
    -0.07
    横
    -0.07
    oola
    -0.06
    ando
    -0.06
    ALTH
    -0.06
     mess
    -0.06
     bulk
    -0.06
    bies
    -0.06
     Zust
    -0.06
     pron
    -0.06
    POSITIVE LOGITS
     preparation
    0.07
    acl
    0.07
     prepar
    0.07
     chuẩn
    0.07
     нада
    0.07
    ingham
    0.07
    acyj
    0.07
    ãĤ¾
    0.07
     coma
    0.07
    oldur
    0.07
    Activations Density 0.032%

    No Known Activations