© 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. 60410
    Prev
    Next
    INDEX
    Explanations

    _information related to astronomical measurements and celestial objects._

    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
    asia
    -0.09
    kontakte
    -0.08
    äºŃ
    -0.07
    IMER
    -0.07
    ãĥŃãĥ¼
    -0.07
    adia
    -0.07
     Dün
    -0.07
    ACHI
    -0.07
    orgot
    -0.07
    OMPI
    -0.07
    POSITIVE LOGITS
     ingres
    0.06
     faint
    0.06
    eree
    0.05
     err
    0.05
    desc
    0.05
     Henri
    0.05
     Forbes
    0.05
    adr
    0.05
    ikit
    0.05
     Sanders
    0.05
    Activations Density 0.014%

    No Known Activations