© 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. 79439
    Prev
    Next
    INDEX
    Explanations

    instances of the word "In" and variations indicating sequencing or addition

    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
    erty
    -0.07
    alias
    -0.07
    ries
    -0.07
    اÙģØ©
    -0.06
    ect
    -0.06
    ToggleButton
    -0.06
    ritte
    -0.06
    loggedin
    -0.06
    _ENDIAN
    -0.06
    igh
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.08
    uder
    0.07
    otel
    0.07
     ALSO
    0.07
    ted
    0.07
    ÙĬÙĥÙĬ
    0.07
     recently
    0.06
    γοÏħ
    0.06
    pressed
    0.06
     also
    0.06
    Activations Density 0.025%

    No Known Activations