© 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 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. 17-LLAMASCOPE-RES-131K
    11. 56058
    Prev
    Next
    INDEX
    Explanations

    references to booths in various contexts

    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
    oeff
    -0.08
    оÑģÑĥд
    -0.07
    otta
    -0.07
     Examiner
    -0.07
    éĻĦ
    -0.06
    atra
    -0.06
    pher
    -0.06
    onda
    -0.06
    ung
    -0.06
    /validation
    -0.06
    POSITIVE LOGITS
    iday
    0.09
    marks
    0.08
    itory
    0.07
    /table
    0.07
    InnerText
    0.07
    eteria
    0.07
    jÃŃ
    0.06
    stop
    0.06
    swith
    0.06
    ForResult
    0.06
    Activations Density 0.008%

    No Known Activations