© 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. 2548
    Prev
    Next
    INDEX
    Explanations

    references to leadership qualities and the impact of strong community connections

    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
    絡
    -0.06
    èĥ
    -0.06
    quier
    -0.06
    amber
    -0.06
    chner
    -0.06
    haps
    -0.06
    arget
    -0.06
    orno
    -0.06
    ำ
    -0.06
    째
    -0.05
    POSITIVE LOGITS
    oot
    0.08
    ibar
    0.08
     manner
    0.07
    abad
    0.07
     way
    0.07
    INCLUDED
    0.06
     amount
    0.06
     havoc
    0.06
     thing
    0.06
     vids
    0.06
    Activations Density 0.160%

    No Known Activations