© 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. 39607
    Prev
    Next
    INDEX
    Explanations

    the word "as" 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
    .fp
    -0.07
    WARN
    -0.07
    km
    -0.07
    nt
    -0.07
    igne
    -0.06
    ÑĸÑĶ
    -0.06
     Lansing
    -0.06
    оÑĢÑĤ
    -0.06
    .dsl
    -0.06
    plementation
    -0.06
    POSITIVE LOGITS
     there
    0.10
     it
    0.09
     they
    0.07
    there
    0.07
     because
    0.07
    because
    0.07
    uluk
    0.07
    ndl
    0.06
     There
    0.06
    since
    0.06
    Activations Density 0.051%

    No Known Activations