© 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. 22-LLAMASCOPE-RES-131K
    6. 3771
    Prev
    Next
    INDEX
    Explanations

    references to psychological concepts and practices

    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
     Gy
    -0.07
    sik
    -0.07
    traits
    -0.06
    _elems
    -0.06
    èīĩ
    -0.06
    nte
    -0.06
     راÙĩ
    -0.06
    310
    -0.06
     extr
    -0.06
     sacrifices
    -0.06
    POSITIVE LOGITS
     tapping
    0.11
    .AF
    0.07
     tapped
    0.07
    lore
    0.07
     tap
    0.07
     ener
    0.07
    رÛĮاÙĨ
    0.07
    reesome
    0.06
    eft
    0.06
    tap
    0.06
    Activations Density 0.000%

    No Known Activations