© 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. 15-LLAMASCOPE-RES-131K
    11. 86627
    Prev
    Next
    INDEX
    Explanations

    references to divine concepts and expressions of faith or hope

    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
    OTO
    -0.06
    ter
    -0.06
     Parr
    -0.06
     Mer
    -0.05
    er
    -0.05
     M
    -0.05
     Martins
    -0.05
     Thr
    -0.05
    Hints
    -0.05
    inary
    -0.05
    POSITIVE LOGITS
    ustil
    0.09
    endon
    0.09
    eneg
    0.08
    alink
    0.08
    otime
    0.08
    Ïħγ
    0.07
    arkan
    0.07
     Hindered
    0.07
    glich
    0.07
    elsen
    0.07
    Activations Density 0.004%

    No Known Activations