© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60051
    Prev
    Next
    INDEX
    Explanations

    terminology and constructs related to mathematical modeling and evaluation in computational contexts

    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
    aby
    -0.06
     smo
    -0.06
     parity
    -0.06
    纪
    -0.05
    ponge
    -0.05
    çľī
    -0.05
     kidnapping
    -0.05
    ench
    -0.05
    ucher
    -0.05
    run
    -0.05
    POSITIVE LOGITS
    ilig
    0.07
    ForResource
    0.07
    UILDER
    0.07
    RITE
    0.07
     Mobility
    0.07
    CGSize
    0.07
    imson
    0.07
    Mob
    0.07
     Metrics
    0.07
     Coverage
    0.07
    Activations Density 0.004%

    No Known Activations