© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26788
    Prev
    Next
    INDEX
    Explanations

    themes related to loss and personal belongings

    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
    readcr
    -0.07
     rec
    -0.07
    ESCO
    -0.06
    åľ¨çº¿è§Ĥçľĭ
    -0.06
    fac
    -0.06
     version
    -0.06
    ãĥ£
    -0.06
    vey
    -0.06
    ificio
    -0.06
     available
    -0.06
    POSITIVE LOGITS
     sentimental
    0.07
     household
    0.07
    odon
    0.06
    obuf
    0.06
    -unused
    0.06
    -NLS
    0.06
    uffle
    0.06
    orz
    0.06
    ÅĤu
    0.06
    ulfilled
    0.06
    Activations Density 0.014%

    No Known Activations