© 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. 58512
    Prev
    Next
    INDEX
    Explanations

    references to future possibilities or scenarios

    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
    zilla
    -0.09
    sons
    -0.08
    shed
    -0.08
    eters
    -0.07
    avec
    -0.07
    üss
    -0.07
     hete
    -0.07
    soever
    -0.07
    ilon
    -0.07
    abras
    -0.07
    POSITIVE LOGITS
     tense
    0.10
    -proof
    0.08
    most
    0.08
    /current
    0.08
    /new
    0.08
     Duffy
    0.07
    /back
    0.07
    -facing
    0.07
    -oriented
    0.07
    -generation
    0.07
    Activations Density 0.023%

    No Known Activations