© 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. 126774
    Prev
    Next
    INDEX
    Explanations

    references to political and socio-economic structures

    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
    (er
    -0.07
    ÌĨ
    -0.07
    rowsable
    -0.07
    RuntimeObject
    -0.07
     Serif
    -0.06
    okud
    -0.06
    μÎŃ
    -0.06
    çIJĨçͱ
    -0.06
    oÅĻ
    -0.06
     vá»įng
    -0.06
    POSITIVE LOGITS
     aforementioned
    0.07
    iel
    0.06
    tical
    0.06
    nic
    0.06
     called
    0.06
    awning
    0.06
    аÑĤелÑĮно
    0.06
    heimer
    0.06
     emailAddress
    0.06
     англ
    0.05
    Activations Density 0.024%

    No Known Activations