© 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. 9-LLAMASCOPE-RES-131K
    11. 97728
    Prev
    Next
    INDEX
    Explanations

    financial burdens and costs associated with various situations

    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
     Bless
    -0.06
    _allocate
    -0.05
     putt
    -0.05
    stein
    -0.05
     bump
    -0.05
     mole
    -0.05
     à¤ħव
    -0.05
     Ash
    -0.05
     дÑĥÑħ
    -0.05
    _circle
    -0.05
    POSITIVE LOGITS
    $MESS
    0.08
    alink
    0.07
    Ñıд
    0.07
    TASK
    0.07
    SWG
    0.07
    aData
    0.07
    ordion
    0.07
    asString
    0.07
    asic
    0.07
    ulk
    0.07
    Activations Density 0.052%

    No Known Activations