© 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. 15-LLAMASCOPE-RES-131K
    11. 40
    Prev
    Next
    INDEX
    Explanations

    occurrences of relationships, particularly those involving issues of consent and legal implications

    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
     premises
    -0.07
    ysi
    -0.06
     Lun
    -0.06
     substantive
    -0.06
     Barry
    -0.06
    ecut
    -0.05
    bcrypt
    -0.05
    erli
    -0.05
    andles
    -0.05
    rc
    -0.05
    POSITIVE LOGITS
     Worlds
    0.07
    Äįet
    0.07
    ios
    0.07
    obel
    0.07
    ucha
    0.07
    /inet
    0.07
    ETHER
    0.06
    ë§ĮëĤ¨
    0.06
    etwork
    0.06
    InterfaceOrientation
    0.06
    Activations Density 0.023%

    No Known Activations