© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128692
    Prev
    Next
    INDEX
    Explanations

    words related to leadership roles and positions

    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
    аÑĢам
    -0.08
    ãĤ¦ãĤ¹
    -0.07
     addCriterion
    -0.07
    vie
    -0.07
    VML
    -0.07
    staking
    -0.07
    WithMany
    -0.07
    OLEAN
    -0.07
     DateFormatter
    -0.07
     ComVisible
    -0.07
    POSITIVE LOGITS
     till
    0.07
     until
    0.07
    elin
    0.06
    1
    0.06
    quet
    0.06
     serve
    0.06
    oped
    0.06
    goo
    0.06
    warts
    0.06
    ~
    0.05
    Activations Density 0.016%

    No Known Activations