© 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. 78565
    Prev
    Next
    INDEX
    Explanations

    words related to defining or establishing legal or moral standards

    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
    inkel
    -0.07
    μÎŃ
    -0.07
    еÑĢп
    -0.07
    au
    -0.07
    ully
    -0.07
    trace
    -0.07
    ett
    -0.07
    .Hex
    -0.06
    omm
    -0.06
    TRACE
    -0.06
    POSITIVE LOGITS
     Ñģобой
    0.11
    amt
    0.08
     ÑģобоÑİ
    0.07
    vfs
    0.07
    endir
    0.07
    cribe
    0.06
    857
    0.06
    DoubleClick
    0.06
    ambia
    0.06
    ngrx
    0.06
    Activations Density 0.006%

    No Known Activations