© 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. 104699
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional experiences and human connection

    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
    apse
    -0.07
    hled
    -0.07
    asal
    -0.07
    á»ĥn
    -0.07
    ixer
    -0.07
    obraz
    -0.07
    onet
    -0.07
    ordes
    -0.07
    etÃŃ
    -0.07
    ůr
    -0.07
    POSITIVE LOGITS
     talk
    0.11
     spoken
    0.10
     discussion
    0.10
     talked
    0.09
     talking
    0.09
     conversation
    0.09
     listening
    0.09
    talk
    0.09
     discussing
    0.09
     words
    0.09
    Activations Density 0.092%

    No Known Activations