© 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. 77475
    Prev
    Next
    INDEX
    Explanations

    references to political parties and their roles in government formation

    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
     kå
    -0.09
    .intellij
    -0.08
    ìĿ´ìĬ¤
    -0.07
    aset
    -0.07
    annon
    -0.07
    æļ
    -0.07
    매
    -0.07
     damer
    -0.06
    IOC
    -0.06
     khô
    -0.06
    POSITIVE LOGITS
     parties
    0.09
     Parties
    0.07
     Altern
    0.07
     novelty
    0.06
    tright
    0.06
     traditional
    0.06
     Green
    0.06
     Traditional
    0.06
     candidates
    0.06
     threshold
    0.06
    Activations Density 0.016%

    No Known Activations