© 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. 117665
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "with" followed by various nouns or phrases that signify collaboration or association

    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
    oli
    -0.07
    notated
    -0.07
     inh
    -0.06
     obsess
    -0.06
    tol
    -0.06
    cv
    -0.06
    uses
    -0.06
     bet
    -0.06
    zym
    -0.05
    otal
    -0.05
    POSITIVE LOGITS
    eyin
    0.08
     plan
    0.08
    rosso
    0.08
    getti
    0.07
    953
    0.07
     plans
    0.07
    icer
    0.07
     gusto
    0.07
    932
    0.07
    izon
    0.07
    Activations Density 0.011%

    No Known Activations