© 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. 72299
    Prev
    Next
    INDEX
    Explanations

    references to entities and actions involving "it" and "they"

    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
    abwe
    -0.07
    æijĺ
    -0.07
    ãĥ¼ãĥĵ
    -0.07
    одо
    -0.07
     Bilg
    -0.07
    éĻ°
    -0.07
    erus
    -0.07
    ÙĦÙĬÙĩ
    -0.07
    Å©
    -0.07
    adata
    -0.07
    POSITIVE LOGITS
    ief
    0.06
     DISCLAIM
    0.06
     occur
    0.06
     èŤ
    0.06
    odÄĽ
    0.05
    istry
    0.05
     crypt
    0.05
     occurred
    0.05
     ca
    0.05
    prü
    0.05
    Activations Density 0.009%

    No Known Activations