Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29452
    Prev
    Next
    INDEX
    Explanations

    discussions about international relations and human rights 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
    jong
    -0.07
    aret
    -0.07
    _emails
    -0.06
    anye
    -0.06
     wet
    -0.06
    akedown
    -0.06
    aleb
    -0.06
     blamed
    -0.06
     layouts
    -0.06
     Newsp
    -0.05
    POSITIVE LOGITS
     trade
    0.07
     human
    0.07
     visa
    0.07
    landa
    0.07
     dém
    0.07
    .openConnection
    0.07
     Foreign
    0.07
     Thương
    0.07
     voc
    0.07
    _foreign
    0.07
    Activations Density 0.022%

    No Known Activations