© 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. 56235
    Prev
    Next
    INDEX
    Explanations

    references to academic journal details and citation formats

    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
    iland
    -0.07
    uron
    -0.07
    APTER
    -0.07
    iffe
    -0.06
    arp
    -0.06
    ãģĶ
    -0.06
    1
    -0.06
    SOLE
    -0.06
    emony
    -0.06
    mund
    -0.06
    POSITIVE LOGITS
    ModelProperty
    0.08
    ó
    0.07
    StartElement
    0.07
    SGlobal
    0.07
    ModelIndex
    0.07
    _permalink
    0.07
    gMaps
    0.07
    PathComponent
    0.07
    æľŁ
    0.07
     impro
    0.07
    Activations Density 0.025%

    No Known Activations