© 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. 17669
    Prev
    Next
    INDEX
    Explanations

    the word "that" in various contexts

    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
    658
    -0.07
    vertis
    -0.06
    pton
    -0.06
    peg
    -0.06
    anst
    -0.06
     infinit
    -0.05
    unt
    -0.05
    ãģ®åŃIJ
    -0.05
     leadership
    -0.05
    gid
    -0.05
    POSITIVE LOGITS
    arov
    0.07
    ê°ij
    0.06
    üf
    0.06
    thane
    0.06
    amage
    0.06
    oproject
    0.06
    .struct
    0.06
    νοÏħ
    0.06
    ÑĩаÑģÑĤ
    0.06
     Äijôi
    0.06
    Activations Density 0.000%

    No Known Activations