© 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. 17-LLAMASCOPE-RES-131K
    11. 59840
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or association

    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
    èŃľ
    -0.07
    /ms
    -0.07
    -fw
    -0.07
    ró
    -0.07
     ciz
    -0.07
    åł¡
    -0.07
    ãĤ¦ãĥĪ
    -0.07
    chw
    -0.07
    жÑĥ
    -0.07
    sert
    -0.07
    POSITIVE LOGITS
     conventional
    0.09
     traditional
    0.09
     physical
    0.07
     usual
    0.07
     actual
    0.07
     Traditional
    0.06
     normal
    0.06
     Blind
    0.06
    ties
    0.06
     fuss
    0.06
    Activations Density 0.005%

    No Known Activations