© 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. 9-LLAMASCOPE-RES-131K
    11. 96971
    Prev
    Next
    INDEX
    Explanations

    words related to impressions and their descriptions

    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
    ways
    -0.09
    istrovstvÃŃ
    -0.09
    abet
    -0.07
    epy
    -0.07
    elp
    -0.07
    ktop
    -0.07
    tems
    -0.07
    -found
    -0.06
    обÑĢаÐ
    -0.06
    té
    -0.06
    POSITIVE LOGITS
    ively
    0.10
    mong
    0.07
    .bootstrapcdn
    0.07
     Pods
    0.07
    anter
    0.07
     davran
    0.07
    ulse
    0.07
    les
    0.07
    476
    0.07
    ESSAGES
    0.07
    Activations Density 0.010%

    No Known Activations