© 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. 89518
    Prev
    Next
    INDEX
    Explanations

    references to professional guidance or advice

    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
     addCriterion
    -0.09
    (UnityEngine
    -0.08
    aqu
    -0.07
    éĺħ读次æķ°
    -0.07
    agini
    -0.07
    hiba
    -0.07
    gere
    -0.07
    zel
    -0.07
    OKIE
    -0.07
    EEK
    -0.07
    POSITIVE LOGITS
     experienced
    0.09
     sympathetic
    0.06
     Spieler
    0.06
     lic
    0.06
     incor
    0.06
     licensed
    0.06
     us
    0.06
     retained
    0.06
    ÙĬÙĨا
    0.05
    atoon
    0.05
    Activations Density 0.013%

    No Known Activations