© 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 EvalsExportsinterp-engineNEWAPI 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. 17737
    Prev
    Next
    INDEX
    Explanations

    philosophical concepts related to the soul and its journey towards a higher existence

    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
    ikal
    -0.08
    wers
    -0.07
    abaj
    -0.07
    coli
    -0.07
    frau
    -0.07
    άνι
    -0.07
    krom
    -0.07
    ylene
    -0.07
    filme
    -0.07
    isman
    -0.07
    POSITIVE LOGITS
     Lesbian
    0.06
     Abyss
    0.06
    acd
    0.05
    (klass
    0.05
    yd
    0.05
     occupations
    0.05
    entiful
    0.05
    λεί
    0.05
     cocks
    0.05
    kov
    0.05
    Activations Density 0.004%

    No Known Activations