© 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. 42293
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Latest."

    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
    наÑĢÑĥж
    -0.08
    _parameters
    -0.07
    orno
    -0.07
    _DENIED
    -0.06
    ipel
    -0.06
    ordes
    -0.06
     dne
    -0.06
    481
    -0.06
    _notice
    -0.06
    iad
    -0.06
    POSITIVE LOGITS
    atically
    0.07
     Robbins
    0.07
    æĹı
    0.06
    ndl
    0.06
    SCP
    0.06
    FG
    0.06
    676
    0.06
    odega
    0.06
    ihad
    0.06
    edes
    0.06
    Activations Density 0.003%

    No Known Activations