© 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. 1716
    Prev
    Next
    INDEX
    Explanations

    themes related to trust and personal growth

    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
    OrElse
    -0.08
    ehler
    -0.08
    chw
    -0.08
    Smarty
    -0.08
    anga
    -0.08
    ediator
    -0.08
     zdrav
    -0.08
    Wizard
    -0.08
    ÄĻż
    -0.08
    볤ìļĶ
    -0.07
    POSITIVE LOGITS
     tonight
    0.06
     shall
    0.06
    m
    0.06
    1
    0.06
    -
    0.05
     rid
    0.05
    -↵
    0.05
     p
    0.05
     geopolitical
    0.05
    in
    0.05
    Activations Density 0.010%

    No Known Activations