© 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. 126498
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers or codes related to entities

    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
    @js
    -0.08
    vsp
    -0.07
    onu
    -0.07
    áo
    -0.07
    @n
    -0.07
    umont
    -0.07
    kır
    -0.07
    vfs
    -0.07
    uw
    -0.07
    ZO
    -0.07
    POSITIVE LOGITS
    idas
    0.07
    wards
    0.06
    rag
    0.06
    ados
    0.06
    ward
    0.06
    WARDS
    0.06
     Ritch
    0.05
     Craft
    0.05
    ieux
    0.05
    space
    0.05
    Activations Density 0.003%

    No Known Activations