© 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. 69696
    Prev
    Next
    INDEX
    Explanations

    phrases related to data presentation and decision-making

    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
    enery
    -0.07
    ãĤ¶ãĥ¼
    -0.06
     mans
    -0.06
    legg
    -0.06
    ãģĹãĤĥ
    -0.06
     Wenger
    -0.06
    rick
    -0.06
    åĿĤ
    -0.05
    inden
    -0.05
    asta
    -0.05
    POSITIVE LOGITS
    ustil
    0.07
     Kad
    0.07
     >č↵
    0.07
    iegel
    0.07
    Macro
    0.07
    viso
    0.07
    Jvm
    0.06
    .Compare
    0.06
    imit
    0.06
    ÑĮ
    0.06
    Activations Density 0.007%

    No Known Activations