© 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. 54151
    Prev
    Next
    INDEX
    Explanations

    references to personnel changes and relationships

    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
    481
    -0.06
    ilden
    -0.06
    907
    -0.06
    IER
    -0.06
    amas
    -0.06
    аÑĢан
    -0.06
    /we
    -0.06
    Gatt
    -0.06
     credit
    -0.06
     Richards
    -0.06
    POSITIVE LOGITS
     married
    0.07
     older
    0.07
    олоÑĤ
    0.07
    akov
    0.06
    ifes
    0.06
    avic
    0.06
    ắc
    0.06
    oldem
    0.06
     Cru
    0.06
    Assignable
    0.06
    Activations Density 0.032%

    No Known Activations