© 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. 92855
    Prev
    Next
    INDEX
    Explanations

    phrases expressing vulnerability and personal struggle

    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
    Legend
    -0.07
    .pp
    -0.06
     Legend
    -0.06
    ichi
    -0.06
    cae
    -0.06
     Mild
    -0.06
    ControlEvents
    -0.06
     FAG
    -0.06
     PIC
    -0.06
    553
    -0.06
    POSITIVE LOGITS
    以为
    0.10
     thought
    0.10
    thought
    0.10
    Thought
    0.09
     despair
    0.09
     Thought
    0.09
     feared
    0.09
     wondered
    0.08
     threatened
    0.08
     seemed
    0.08
    Activations Density 0.114%

    No Known Activations