© 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. 87189
    Prev
    Next
    INDEX
    Explanations

    references to political figures and administrations

    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
    oda
    -0.08
    WRAPPER
    -0.08
    istrovstvÃŃ
    -0.07
     IsNot
    -0.07
    esson
    -0.07
    çĴĥ
    -0.07
    kowski
    -0.07
    _marshall
    -0.07
     pione
    -0.07
    essen
    -0.07
    POSITIVE LOGITS
     government
    0.08
     administration
    0.08
    era
    0.07
    team
    0.07
     team
    0.07
    aler
    0.07
     Administration
    0.06
    -team
    0.06
     era
    0.06
    -era
    0.06
    Activations Density 0.011%

    No Known Activations