© 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. 93493
    Prev
    Next
    INDEX
    Explanations

    references to the term "Delta" in various contexts, likely indicating a focus on specific topics associated with change or progress

    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
    seau
    -0.10
    nee
    -0.09
    ADS
    -0.08
    orda
    -0.08
    linky
    -0.08
    innacle
    -0.08
    ëĵĿ
    -0.08
    erable
    -0.08
    plevel
    -0.08
    862
    -0.08
    POSITIVE LOGITS
    ted
    0.07
    ting
    0.07
    fine
    0.06
    angelo
    0.06
     Mans
    0.06
    ence
    0.06
    -wide
    0.06
    on
    0.06
    e
    0.06
    aven
    0.05
    Activations Density 0.033%

    No Known Activations