© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88879
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expressions of love or desire

    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
    wit
    -0.06
     Aston
    -0.06
     Jacobs
    -0.06
    ARSE
    -0.06
     hypothesis
    -0.06
    askan
    -0.05
     unofficial
    -0.05
    chop
    -0.05
    inas
    -0.05
    _INITIAL
    -0.05
    POSITIVE LOGITS
     currently
    0.08
     Äijang
    0.07
    currently
    0.07
    NN
    0.07
    ODY
    0.07
     Currently
    0.07
    Currently
    0.07
    afc
    0.07
    isoft
    0.07
    PPP
    0.07
    Activations Density 0.015%

    No Known Activations