© 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. 15-LLAMASCOPE-RES-131K
    11. 87904
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical and scientific formalism, particularly in the context of laws and rights

    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
    icia
    -0.06
    ivos
    -0.06
    apl
    -0.06
    oÄŁ
    -0.06
    nist
    -0.05
     planta
    -0.05
     collo
    -0.05
    kie
    -0.05
    ff
    -0.05
    kor
    -0.05
    POSITIVE LOGITS
    slaught
    0.08
    jÃŃm
    0.08
     vá»ģ
    0.07
    ãģķãģĦ
    0.07
    å¾
    0.06
    ãĤ¹ãĤ¯
    0.06
    .hr
    0.06
    everything
    0.06
    _sock
    0.06
    .Misc
    0.06
    Activations Density 0.091%

    No Known Activations