© 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. 5-LLAMASCOPE-RES-131K
    11. 125833
    Prev
    Next
    INDEX
    Explanations

    possessive phrases, particularly relating to family members

    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
    alo
    -0.07
    urt
    -0.07
    asan
    -0.07
    ener
    -0.06
    akes
    -0.06
     Tre
    -0.06
    .mime
    -0.06
    MF
    -0.06
     ext
    -0.06
    vre
    -0.06
    POSITIVE LOGITS
    UFFIX
    0.07
    ÙĪاÙĩ
    0.07
    rial
    0.07
    ±Ð¾ÑĤ
    0.07
    ableView
    0.07
    /raw
    0.06
    bedtls
    0.06
    ÑĪÑĤ
    0.06
    .onView
    0.06
    rieve
    0.06
    Activations Density 0.009%

    No Known Activations