© 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. 119145
    Prev
    Next
    INDEX
    Explanations

    references to political conflict and governmental actions

    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
     “âĢ¦
    -0.07
    ateway
    -0.07
    peare
    -0.07
    adia
    -0.07
    phet
    -0.07
    enger
    -0.06
    mons
    -0.06
    opc
    -0.06
    anie
    -0.06
    alnız
    -0.06
    POSITIVE LOGITS
     Wednesday
    0.07
     Thursday
    0.06
    ापन
    0.06
    fluid
    0.06
     resets
    0.06
     needle
    0.06
     Friday
    0.06
    å¤ļå°ij
    0.06
    dana
    0.05
    fusion
    0.05
    Activations Density 0.009%

    No Known Activations