© 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. 27267
    Prev
    Next
    INDEX
    Explanations

    elements related to architectural design and innovative space usage

    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
    trand
    -0.07
    itized
    -0.07
    xdc
    -0.07
    ÏĮÏģ
    -0.07
    ossa
    -0.07
    itm
    -0.07
    deo
    -0.07
     Lager
    -0.07
    _OCCURRED
    -0.06
    izz
    -0.06
    POSITIVE LOGITS
     project
    0.07
     house
    0.07
     Summer
    0.06
     summer
    0.06
    eref
    0.06
     è±
    0.06
     design
    0.06
    -project
    0.06
    akis
    0.05
    elier
    0.05
    Activations Density 0.027%

    No Known Activations