© 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. 123730
    Prev
    Next
    INDEX
    Explanations

    references to teamwork and support in relation to personal and legal assistance

    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
    adin
    -0.08
    zcze
    -0.08
     nackte
    -0.07
    urger
    -0.07
    kker
    -0.06
    iaux
    -0.06
    ".$_
    -0.06
     neither
    -0.06
    aho
    -0.06
    íĥĿ
    -0.06
    POSITIVE LOGITS
     including
    0.07
    asi
    0.06
    اÙĦات
    0.06
    irket
    0.06
    aby
    0.06
    voy
    0.06
    otropic
    0.05
    بÙĪÙĦ
    0.05
    ke
    0.05
    avings
    0.05
    Activations Density 0.003%

    No Known Activations