© 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. 61417
    Prev
    Next
    INDEX
    Explanations

    mentions of product recalls and safety-related information

    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
    械
    -0.07
    (ع
    -0.07
    avir
    -0.06
    ìĺ¥
    -0.06
    AFX
    -0.06
    .scalablytyped
    -0.06
    Destructor
    -0.06
    пп
    -0.06
    gaard
    -0.06
    è°·
    -0.06
    POSITIVE LOGITS
     affected
    0.07
     certain
    0.07
    Affected
    0.07
    uptools
    0.07
     flaw
    0.06
     recall
    0.06
     recalled
    0.06
    owners
    0.06
     potentially
    0.06
    dux
    0.06
    Activations Density 0.003%

    No Known Activations