© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60520
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to investigative journalism and reporting

    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
    924
    -0.07
    TB
    -0.07
    icos
    -0.07
     dipping
    -0.06
    çĶº
    -0.06
    ãĥĥ
    -0.06
    ayım
    -0.06
    ì°¸
    -0.06
    icio
    -0.06
    isz
    -0.06
    POSITIVE LOGITS
     sting
    0.07
    Transactional
    0.07
    ÙĪØ¯Ùĩ
    0.07
    ront
    0.07
    egrity
    0.06
    @Resource
    0.06
    abcdefghijkl
    0.06
     migrationBuilder
    0.06
    ekim
    0.06
    opic
    0.06
    Activations Density 0.015%

    No Known Activations