© 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. 9-LLAMASCOPE-RES-131K
    11. 98885
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progression or causation

    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
    .toHexString
    -0.06
    еÑģÑĤи
    -0.06
     themselves
    -0.06
    vise
    -0.06
    aller
    -0.06
    arshal
    -0.06
     instrumental
    -0.06
    IID
    -0.06
    vit
    -0.06
    ÄŁan
    -0.06
    POSITIVE LOGITS
     everywhere
    0.07
    اث
    0.07
    roe
    0.07
    .scalablytyped
    0.07
    AccessException
    0.06
    dff
    0.06
    @protocol
    0.06
    atab
    0.06
     meaning
    0.06
     drv
    0.06
    Activations Density 0.052%

    No Known Activations