© 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. 4295
    Prev
    Next
    INDEX
    Explanations

    references to National Public Radio (NPR) and the BBC

    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
    -gnu
    -0.07
    ajs
    -0.07
     Stub
    -0.07
    etCode
    -0.06
     Stamp
    -0.06
    Stamp
    -0.06
     loc
    -0.06
    stÅĻed
    -0.06
    /apt
    -0.06
     Trap
    -0.05
    POSITIVE LOGITS
    nung
    0.08
    eren
    0.07
    otime
    0.07
    ritch
    0.07
    -badge
    0.06
    werk
    0.06
     Uno
    0.06
    vail
    0.06
    IED
    0.06
    ãĥ³ãĤ¹
    0.06
    Activations Density 0.004%

    No Known Activations