© 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. 17-LLAMASCOPE-RES-131K
    11. 55624
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality or dependency

    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
    ovo
    -0.07
    ghi
    -0.07
    xde
    -0.06
    ÑĢеп
    -0.06
     locker
    -0.06
     Appe
    -0.06
    zar
    -0.06
     Colomb
    -0.06
    iode
    -0.06
     Wich
    -0.06
    POSITIVE LOGITS
     upon
    0.09
    avad
    0.08
     depending
    0.08
     conv
    0.07
    RTC
    0.07
    upon
    0.07
     whether
    0.07
    eya
    0.06
    depending
    0.06
    atore
    0.06
    Activations Density 0.008%

    No Known Activations