© 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. 127016
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize actions aimed at political or social advocacy

    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
    æ¼ı
    -0.08
    دارÛĮ
    -0.07
    apis
    -0.06
    ifest
    -0.06
    æݪ
    -0.06
    ahlen
    -0.06
    {!!
    -0.06
    ãĥ³ãĥ
    -0.06
    896
    -0.06
    IFS
    -0.06
    POSITIVE LOGITS
     against
    0.07
     secure
    0.07
     voice
    0.07
     protect
    0.07
    opy
    0.07
     help
    0.06
     opposed
    0.06
     truth
    0.06
    bane
    0.06
    win
    0.06
    Activations Density 0.023%

    No Known Activations