© 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. 84137
    Prev
    Next
    INDEX
    Explanations

    phrases related to public opinion and preferences

    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
    gles
    -0.07
    bane
    -0.06
    ONENT
    -0.06
    essler
    -0.06
    bots
    -0.06
    ogan
    -0.06
    ëł¹
    -0.06
    wand
    -0.06
    amac
    -0.06
    emd
    -0.06
    POSITIVE LOGITS
     would
    0.08
    would
    0.08
    .future
    0.08
     Would
    0.07
     willingness
    0.07
     kdyby
    0.07
    urer
    0.07
     serait
    0.07
    Would
    0.06
     íĿ¬
    0.06
    Activations Density 0.006%

    No Known Activations