© 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. 94854
    Prev
    Next
    INDEX
    Explanations

    notations indicating nullable and non-nullable data types in programming

    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
    ekk
    -0.07
    encion
    -0.07
    å¨ĺ
    -0.06
    ÑĦоÑĢ
    -0.06
    IDA
    -0.06
    иÑĤа
    -0.06
     Ñĥп
    -0.06
    ida
    -0.06
    kea
    -0.06
    yas
    -0.06
    POSITIVE LOGITS
    URITY
    0.07
    arem
    0.07
    å¹¹ç·ļ
    0.06
     spoil
    0.06
    éĢĶ
    0.06
    atak
    0.06
    /pass
    0.06
     Spo
    0.06
     CWE
    0.06
    elder
    0.06
    Activations Density 0.000%

    No Known Activations