© 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. 9-LLAMASCOPE-RES-131K
    11. 94457
    Prev
    Next
    INDEX
    Explanations

    links or URLs within the text

    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
    \'
    -0.07
     Nadu
    -0.07
    chef
    -0.06
    amat
    -0.06
    edo
    -0.06
    ãĥ£
    -0.06
    uch
    -0.06
     inex
    -0.06
    utzer
    -0.05
     annex
    -0.05
    POSITIVE LOGITS
    нÑıÑĤи
    0.08
    ¦æĥħ
    0.07
    eph
    0.07
    MOTE
    0.07
    tas
    0.07
    iry
    0.07
    toi
    0.07
    arto
    0.07
    ioned
    0.06
     Druh
    0.06
    Activations Density 0.010%

    No Known Activations