© 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. 15-LLAMASCOPE-RES-131K
    6. 279
    Prev
    Next
    INDEX
    Explanations

    concepts related to demonic possession and interactions with humans

    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
    flater
    -0.07
    ackbar
    -0.07
    entai
    -0.07
    irez
    -0.07
    å®
    -0.07
    enstein
    -0.07
    opies
    -0.07
    requete
    -0.06
    ruh
    -0.06
    udget
    -0.06
    POSITIVE LOGITS
    .UnitTesting
    0.07
    lection
    0.06
    unfinished
    0.06
     STDERR
    0.06
     pudd
    0.06
    ä¹Ĺ
    0.06
    uintptr
    0.06
     Bison
    0.06
    CLUD
    0.06
    chl
    0.05
    Activations Density 0.028%

    No Known Activations