© 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. 124395
    Prev
    Next
    INDEX
    Explanations

    references to regulations or legal matters

    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
    oples
    -0.07
     Fr
    -0.06
    ffen
    -0.06
    upport
    -0.06
     Vance
    -0.06
    artial
    -0.06
    shaw
    -0.05
    олоÑĪ
    -0.05
    @gmail
    -0.05
    pon
    -0.05
    POSITIVE LOGITS
     href
    0.08
    _href
    0.08
    href
    0.07
    [href
    0.07
     Santana
    0.07
    Immutable
    0.07
    .lucene
    0.07
     ков
    0.06
    :href
    0.06
    죽
    0.06
    Activations Density 0.000%

    No Known Activations