© 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 EvalsExportsAPI 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. 89121
    Prev
    Next
    INDEX
    Explanations

    negative or restrictive terms related to housing and living conditions

    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
    sko
    -0.07
    .FileSystem
    -0.07
    trinsic
    -0.07
    iggins
    -0.07
     ÅĤ
    -0.06
     WARN
    -0.06
    اتÛĮ
    -0.06
    à¥įवर
    -0.06
    emma
    -0.06
    ilog
    -0.06
    POSITIVE LOGITS
     noise
    0.07
     commercial
    0.07
    é¾Ħ
    0.07
     Noise
    0.07
     competition
    0.06
    crow
    0.06
     draft
    0.06
    pes
    0.06
    wall
    0.06
    rush
    0.06
    Activations Density 0.017%

    No Known Activations