© 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. 124055
    Prev
    Next
    INDEX
    Explanations

    instances of communication and interaction in the narrative

    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
    vit
    -0.08
     háºŃu
    -0.07
    olist
    -0.07
    luk
    -0.07
     seins
    -0.07
     hoc
    -0.06
    lyph
    -0.06
    dac
    -0.06
    ÑģÑĤи
    -0.06
    tout
    -0.06
    POSITIVE LOGITS
     spoke
    0.10
     speak
    0.10
     speaking
    0.08
     broke
    0.08
     speaks
    0.08
     spoken
    0.07
     Speak
    0.07
     voice
    0.07
    allis
    0.07
     break
    0.07
    Activations Density 0.024%

    No Known Activations