© 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. 41277
    Prev
    Next
    INDEX
    Explanations

    statistical data and metrics regarding public opinion

    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
    jÄĻ
    -0.07
    stoff
    -0.07
    ptype
    -0.07
     Millenn
    -0.07
    ån
    -0.07
    ayla
    -0.07
    ())[
    -0.07
    ooke
    -0.07
     JADX
    -0.07
    andez
    -0.06
    POSITIVE LOGITS
     AE
    0.07
     respondents
    0.06
    ħn
    0.06
     overall
    0.06
     gam
    0.06
     survey
    0.06
    ibr
    0.06
     Least
    0.05
    0.05
     kü
    0.05
    Activations Density 0.007%

    No Known Activations