© 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. 61044
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly related to timeframes or quantities

    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
    rait
    -0.08
    jte
    -0.08
    ushman
    -0.07
    ninger
    -0.07
    olls
    -0.07
    .metamodel
    -0.07
     мом
    -0.07
     treff
    -0.07
    jde
    -0.07
    deniz
    -0.07
    POSITIVE LOGITS
    261
    0.06
    adas
    0.06
    465
    0.06
    ether
    0.06
    OnError
    0.06
    elo
    0.06
    riel
    0.05
    lava
    0.05
    726
    0.05
    unter
    0.05
    Activations Density 0.034%

    No Known Activations