© 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 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. 58639
    Prev
    Next
    INDEX
    Explanations

    concepts related to factors influencing decision-making and assessments in various contexts

    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
     etc
    -0.10
    /etc
    -0.08
    etc
    -0.07
     ÑĤоÑīо
    -0.07
    ÑĢив
    -0.07
     atd
    -0.07
     Vz
    -0.07
    Ñħо
    -0.06
    incl
    -0.06
     æIJ
    -0.06
    POSITIVE LOGITS
    :async
    0.08
     yani
    0.08
    anches
    0.07
    á»ijng
    0.06
    661
    0.06
    acic
    0.06
    !
    0.06
     ¶
    0.06
    earch
    0.06
    767
    0.06
    Activations Density 0.309%

    No Known Activations