© 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. 71439
    Prev
    Next
    INDEX
    Explanations

    references to international trade organizations and their policies

    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
     statewide
    -0.07
     beat
    -0.06
     Stacy
    -0.06
     stem
    -0.06
     nationwide
    -0.06
    velope
    -0.06
    -assets
    -0.06
    é¦
    -0.06
     gy
    -0.06
    /native
    -0.06
    POSITIVE LOGITS
    UNCT
    0.08
     Member
    0.07
    lung
    0.07
    attle
    0.07
     Mult
    0.07
    Member
    0.07
     Rounds
    0.06
    -mult
    0.06
     Members
    0.06
    orts
    0.06
    Activations Density 0.018%

    No Known Activations