© 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. 82826
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities and diversity of options

    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
    entlich
    -0.06
    -f
    -0.06
    dia
    -0.05
    åĬ¹
    -0.05
     Boulevard
    -0.05
    mue
    -0.05
    Decorator
    -0.05
    err
    -0.05
    меÑī
    -0.05
     reserves
    -0.05
    POSITIVE LOGITS
    cente
    0.07
     Hermes
    0.07
    èĨ
    0.07
    ENU
    0.07
    nar
    0.07
    ίοÏĤ
    0.07
    _GB
    0.06
    \Block
    0.06
    ignet
    0.06
    ì§ĵ
    0.06
    Activations Density 0.004%

    No Known Activations