© 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. 62174
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional support and understanding

    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
    whatever
    -0.08
     hopefully
    -0.07
    ï¸
    -0.07
    cio
    -0.07
     instead
    -0.07
     Whatever
    -0.06
     whatever
    -0.06
    åı¯èĥ½æĢ§
    -0.06
    Whatever
    -0.06
    anst
    -0.06
    POSITIVE LOGITS
     unless
    0.11
    unless
    0.10
     sometimes
    0.09
     Unless
    0.08
     oneself
    0.08
    sometimes
    0.08
    Unless
    0.08
     anymore
    0.08
    Sometimes
    0.08
     certain
    0.08
    Activations Density 0.052%

    No Known Activations