© 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. 124165
    Prev
    Next
    INDEX
    Explanations

    the word "this" and its variations in different 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
    ewis
    -0.06
    338
    -0.06
    ica
    -0.06
    own
    -0.06
    473
    -0.06
    roup
    -0.06
    opies
    -0.05
    ules
    -0.05
     Pere
    -0.05
    ush
    -0.05
    POSITIVE LOGITS
    ActionCreators
    0.08
    JECT
    0.07
    ,eg
    0.07
    errat
    0.07
     muht
    0.07
    .signals
    0.07
    axon
    0.07
     Onun
    0.07
    ipples
    0.07
    ä¾
    0.07
    Activations Density 0.003%

    No Known Activations