© 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. 130764
    Prev
    Next
    INDEX
    Explanations

    geographic or place-related references

    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
    ournée
    -0.07
    aura
    -0.07
     cuckold
    -0.07
    ãĥ³ãĥĨãĤ£
    -0.07
    ÙĪغ
    -0.07
     æ¼
    -0.07
    pcf
    -0.07
    ÑĢид
    -0.06
    iesel
    -0.06
    APH
    -0.06
    POSITIVE LOGITS
    TM
    0.07
    race
    0.06
     Hom
    0.06
    TB
    0.06
    aves
    0.06
    HEME
    0.06
    onz
    0.06
     Meh
    0.06
     hom
    0.05
     stead
    0.05
    Activations Density 0.008%

    No Known Activations