© 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. 9-LLAMASCOPE-RES-131K
    11. 98018
    Prev
    Next
    INDEX
    Explanations

    issues related to political responsibility and societal obligations

    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
    issan
    -0.06
     Lamp
    -0.06
     Nat
    -0.06
     Ness
    -0.06
     summary
    -0.06
     Im
    -0.06
     Roberts
    -0.06
     Heap
    -0.06
     Essen
    -0.06
     understanding
    -0.05
    POSITIVE LOGITS
    QUOTE
    0.08
     STDCALL
    0.08
     jspb
    0.07
    -Token
    0.07
    yleft
    0.07
    $MESS
    0.07
    qus
    0.07
    ारन
    0.07
    _DECLS
    0.07
    ahu
    0.07
    Activations Density 0.148%

    No Known Activations