© 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. 72945
    Prev
    Next
    INDEX
    Explanations

    themes related to the value and limitations of money and material possessions

    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
    olin
    -0.07
    ryan
    -0.07
    ÙĪار
    -0.06
    resher
    -0.06
    ignKey
    -0.06
    öh
    -0.06
    Longrightarrow
    -0.06
    elman
    -0.06
    alon
    -0.06
    omer
    -0.06
    POSITIVE LOGITS
     cannot
    0.17
    cannot
    0.15
     Cannot
    0.14
    Cannot
    0.12
    æĹłæ³ķ
    0.12
     impossible
    0.11
     imposs
    0.10
    ä¸įèĥ½
    0.10
    åıªèĥ½
    0.10
     нелÑĮзÑı
    0.09
    Activations Density 0.063%

    No Known Activations