© 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 EvalsExportsinterp-engineNEWAPI 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. 81860
    Prev
    Next
    INDEX
    Explanations

    aspects related to policies and guidelines

    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
    ĥn
    -0.07
    onds
    -0.07
    ÙĤاÙħ
    -0.06
    ä¸įå¾Ĺ
    -0.06
    ẽ
    -0.06
    .sponge
    -0.06
    kazy
    -0.06
    antha
    -0.06
    ất
    -0.06
     showDialog
    -0.06
    POSITIVE LOGITS
     instead
    0.21
     Instead
    0.20
    Instead
    0.20
    instead
    0.18
     вмеÑģÑĤ
    0.14
     alternative
    0.10
     better
    0.10
     alternatives
    0.10
     solution
    0.09
     Solution
    0.09
    Activations Density 0.036%

    No Known Activations