© 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 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. 106206
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes and transformations over time

    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
    azio
    -0.07
     groundwork
    -0.06
    jt
    -0.06
    ospels
    -0.06
    xxxxxxxx
    -0.06
    erto
    -0.06
    achten
    -0.06
     ÑģÑĤанÑĥ
    -0.05
     suddenly
    -0.05
    /.
    -0.05
    POSITIVE LOGITS
     various
    0.07
    elere
    0.07
    LAR
    0.07
    еÑĤелÑĮ
    0.07
     Modern
    0.07
    ä¸įæĸŃ
    0.07
    åıĺåĮĸ
    0.07
     modern
    0.07
    aters
    0.07
    ños
    0.07
    Activations Density 0.019%

    No Known Activations