© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 56342
    Prev
    Next
    INDEX
    Explanations

    themes of empowerment 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
    Ľ°
    -0.06
    ATO
    -0.06
    afil
    -0.06
     Uncategorized
    -0.06
    quez
    -0.06
    maz
    -0.06
    zie
    -0.05
    åħ°
    -0.05
    udad
    -0.05
    ORM
    -0.05
    POSITIVE LOGITS
    ë²Į
    0.08
    ifndef
    0.07
    -FIRST
    0.07
    uzzer
    0.07
     ability
    0.07
    åĽ
    0.07
     ActionController
    0.07
    ÙĦØŃ
    0.06
    aucoup
    0.06
    olson
    0.06
    Activations Density 0.070%

    No Known Activations