© 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. 55493
    Prev
    Next
    INDEX
    Explanations

    time and date references

    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
    ocz
    -0.07
    á»ķng
    -0.07
    umer
    -0.06
    immer
    -0.06
    auc
    -0.06
    versible
    -0.06
    eming
    -0.06
    odom
    -0.06
    oc
    -0.06
    лиÑĪ
    -0.06
    POSITIVE LOGITS
     Morg
    0.07
    oust
    0.07
    iron
    0.06
    stein
    0.06
     bul
    0.06
    ££
    0.06
    phies
    0.06
    रण
    0.06
    vida
    0.06
    ELLOW
    0.06
    Activations Density 0.008%

    No Known Activations