© 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. 79373
    Prev
    Next
    INDEX
    Explanations

    phrases related to liability and legal disclaimers

    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
    pz
    -0.06
     sentiment
    -0.06
    611
    -0.06
     Sent
    -0.06
    implify
    -0.06
    cao
    -0.06
    workspace
    -0.06
     undert
    -0.06
     fine
    -0.06
    èĤ
    -0.06
    POSITIVE LOGITS
    aison
    0.07
    Ħ件
    0.07
    itters
    0.07
     Facility
    0.07
     Facilities
    0.06
    amac
    0.06
    HEAD
    0.06
    ÙĨب
    0.06
     Turing
    0.06
     بÙĨد
    0.06
    Activations Density 0.000%

    No Known Activations