© 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. 118990
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts of interest

    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
    ìķħ
    -0.08
     GUIStyle
    -0.08
    .scalablytyped
    -0.08
    lide
    -0.08
    Äł
    -0.08
     æį
    -0.07
    ëłĩê²Į
    -0.07
    alian
    -0.07
     UIStoryboard
    -0.07
    gart
    -0.07
    POSITIVE LOGITS
    /conf
    0.09
    aland
    0.07
    beck
    0.07
     between
    0.06
     with
    0.06
     management
    0.06
     tam
    0.06
     conflict
    0.06
    ive
    0.06
     p
    0.06
    Activations Density 0.005%

    No Known Activations