© 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. 89079
    Prev
    Next
    INDEX
    Explanations

    questions and conditional statements related to data interactions

    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
    алÑĥ
    -0.07
     capital
    -0.07
     èĩªåĬ¨çĶŁæĪIJ
    -0.07
    åĬŀåħ¬
    -0.06
    andal
    -0.06
     Leban
    -0.06
    .Currency
    -0.06
     Cow
    -0.06
    огод
    -0.06
    mo
    -0.06
    POSITIVE LOGITS
     actual
    0.07
    ngör
    0.06
    å±¥
    0.06
     напÑĢÑıм
    0.06
    technology
    0.06
    ani
    0.06
    eko
    0.06
    onga
    0.06
    orr
    0.06
     technologies
    0.06
    Activations Density 0.004%

    No Known Activations