© 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. 83847
    Prev
    Next
    INDEX
    Explanations

    mentions of media coverage and political commentary

    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
    icos
    -0.06
    erli
    -0.06
    ignum
    -0.06
     UsersController
    -0.06
     announc
    -0.06
    ÑĢеÑħ
    -0.06
    igon
    -0.06
     antic
    -0.06
    ancock
    -0.06
     Ñģка
    -0.06
    POSITIVE LOGITS
     sco
    0.08
     scr
    0.07
     freel
    0.07
    bia
    0.06
    ForObject
    0.06
     оÑģвеÑī
    0.06
    udio
    0.06
     scoop
    0.06
    rost
    0.06
     Press
    0.06
    Activations Density 0.007%

    No Known Activations