© 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. 93010
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and consequences

    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
     **/↵↵
    -0.07
    :["
    -0.07
     cháy
    -0.07
    .createFrom
    -0.07
    !");↵↵
    -0.07
    ÙĤØ·
    -0.07
    ÐķС
    -0.07
    rita
    -0.07
    iglia
    -0.07
     âĹĦ
    -0.07
    POSITIVE LOGITS
     etc
    0.07
     blah
    0.07
    etc
    0.07
     unnamed
    0.06
    emailer
    0.06
     allies
    0.06
     authorities
    0.05
    hest
    0.05
    otec
    0.05
     earlier
    0.05
    Activations Density 0.061%

    No Known Activations