© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119753
    Prev
    Next
    INDEX
    Explanations

    concepts related to safety and protection

    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
     Fucked
    -0.06
    twig
    -0.06
    iero
    -0.06
    SED
    -0.06
    è§ī
    -0.06
    keterangan
    -0.06
    _Invoke
    -0.06
     MetroFramework
    -0.06
    ISTRIBUT
    -0.06
    imenti
    -0.06
    POSITIVE LOGITS
     creation
    0.22
    creation
    0.18
     created
    0.17
     Creation
    0.16
    Creation
    0.15
     formation
    0.15
    created
    0.14
    ãĤĴä½ľ
    0.14
    _creation
    0.13
     production
    0.13
    Activations Density 0.141%

    No Known Activations