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

    Neuronpedia

    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. 82125
    Prev
    Next
    INDEX
    Explanations

    references to jailbreaking and related technical processes

    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
    ema
    -0.09
    UrlParser
    -0.07
    _OBJC
    -0.07
     IID
    -0.07
     reserv
    -0.07
    .Encoding
    -0.07
    shm
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
     Äįt
    -0.07
    dana
    -0.06
    POSITIVE LOGITS
    qq
    0.07
    vil
    0.06
     Boots
    0.06
     power
    0.06
     bypass
    0.06
     thủ
    0.06
     onActivityResult
    0.06
    uhn
    0.05
     jail
    0.05
    ooter
    0.05
    Activations Density 0.007%

    No Known Activations