© 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. 60805
    Prev
    Next
    INDEX
    Explanations

    language related to governmental processes and transparency

    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
     MAY
    -0.07
    cial
    -0.07
    agara
    -0.07
    lob
    -0.06
     Forge
    -0.06
    ëĿ¼ëıĦ
    -0.06
    kü
    -0.06
    573
    -0.06
    quina
    -0.06
     might
    -0.06
    POSITIVE LOGITS
     exactly
    0.07
     nowhere
    0.07
     precisely
    0.07
     scr
    0.06
     contrary
    0.06
     perfectly
    0.06
    .transparent
    0.06
     btw
    0.06
     relevant
    0.06
     every
    0.06
    Activations Density 0.017%

    No Known Activations