© 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. 78403
    Prev
    Next
    INDEX
    Explanations

    locations and places mentioned in the text

    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
    ÙıÙĪا
    -0.07
     Baghd
    -0.07
    foot
    -0.07
    onth
    -0.07
    antal
    -0.06
    andi
    -0.06
    æĶĿ
    -0.06
    ledo
    -0.06
    ena
    -0.06
    çĤ¸
    -0.06
    POSITIVE LOGITS
    imei
    0.07
     Europe
    0.06
    zel
    0.06
     arenas
    0.06
    APA
    0.06
    Ordered
    0.06
    epad
    0.06
    acin
    0.06
     cities
    0.06
     Anc
    0.06
    Activations Density 0.018%

    No Known Activations