© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60522
    Prev
    Next
    INDEX
    Explanations

    themes of character development 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
    olly
    -0.06
    usz
    -0.06
    echan
    -0.06
    avana
    -0.06
    ëŀĺ
    -0.06
    atica
    -0.06
    essler
    -0.05
    ix
    -0.05
     ease
    -0.05
     Share
    -0.05
    POSITIVE LOGITS
    rens
    0.07
     charm
    0.07
    adox
    0.07
    ibel
    0.07
    BCM
    0.07
     precisely
    0.07
     Charm
    0.06
    ormsg
    0.06
    DMI
    0.06
    è·Į
    0.06
    Activations Density 0.045%

    No Known Activations