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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2051
    Prev
    Next
    INDEX
    Explanations

    phrases indicating partisan bias and manipulation of narratives

    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
     inclusive
    -0.06
    oop
    -0.06
    bers
    -0.06
    اÙĤ
    -0.06
     valid
    -0.06
     physical
    -0.06
     Grace
    -0.05
    alous
    -0.05
    578
    -0.05
     Schneider
    -0.05
    POSITIVE LOGITS
    знаÑĩа
    0.07
     insp
    0.07
    _FUNCTIONS
    0.07
    itto
    0.07
     loyalty
    0.07
    ustry
    0.07
    ufact
    0.07
    -prepend
    0.07
    emouth
    0.07
     stockholm
    0.07
    Activations Density 0.039%

    No Known Activations