© 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. 9-LLAMASCOPE-RES-131K
    11. 98279
    Prev
    Next
    INDEX
    Explanations

    terms related to legal penalties and sentencing

    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
    weg
    -0.08
    querque
    -0.07
     NavParams
    -0.07
    spÄĽ
    -0.07
    igo
    -0.06
    lander
    -0.06
    aÄį
    -0.06
    rowsers
    -0.06
    ÙĪÙĦÙĩ
    -0.06
     fest
    -0.06
    POSITIVE LOGITS
    uffix
    0.08
    etr
    0.08
    ãĤ¹ãĥĨãĤ£
    0.07
    ee
    0.07
    325
    0.07
    "crypto
    0.07
    eer
    0.07
    ãĥĥãĥī
    0.06
    ovan
    0.06
    BuilderInterface
    0.06
    Activations Density 0.006%

    No Known Activations