© 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 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. 16417
    Prev
    Next
    INDEX
    Explanations

    phrases relating to aging and the challenges faced by the elderly

    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
    ilon
    -0.06
     ped
    -0.06
    ashboard
    -0.06
    annon
    -0.06
    cke
    -0.06
    ivar
    -0.06
    izoph
    -0.06
    nicos
    -0.06
    urai
    -0.06
    ickle
    -0.06
    POSITIVE LOGITS
     mobility
    0.10
     Mobility
    0.09
    Independ
    0.08
    Mob
    0.08
    afety
    0.08
    mob
    0.08
     independence
    0.08
    Safety
    0.07
     independ
    0.07
    immel
    0.07
    Activations Density 0.003%

    No Known Activations