© 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. 29407
    Prev
    Next
    INDEX
    Explanations

    numerical or statistical references in text

    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
    oya
    -0.08
    Å¡t
    -0.07
    versions
    -0.07
    rama
    -0.07
    elta
    -0.06
    oningen
    -0.06
    DITION
    -0.06
    /stdc
    -0.06
     elaborate
    -0.06
    oa
    -0.06
    POSITIVE LOGITS
    ernel
    0.07
    rens
    0.06
    -Star
    0.06
    _mA
    0.06
    _tA
    0.06
     Seks
    0.06
    _tF
    0.06
    .scalablytyped
    0.06
    ÑĢÑĥÑĤ
    0.06
    wig
    0.06
    Activations Density 0.001%

    No Known Activations