© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83449
    Prev
    Next
    INDEX
    Explanations

    phrases related to ideological constructs and their implications

    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
    ocker
    -0.07
    âij
    -0.07
    veÅĻej
    -0.07
    spam
    -0.07
     encount
    -0.07
    ’ÑĶ
    -0.07
    conti
    -0.07
    abı
    -0.07
    plist
    -0.06
    νοÏħ
    -0.06
    POSITIVE LOGITS
     something
    0.07
     unspecified
    0.07
     indeed
    0.07
    esson
    0.07
     etc
    0.06
    ..
    0.06
     anything
    0.06
     blah
    0.06
    etc
    0.06
     itself
    0.06
    Activations Density 0.028%

    No Known Activations