© 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. 78922
    Prev
    Next
    INDEX
    Explanations

    phrases associated with personal interactions and meetings

    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
    uj
    -0.07
    éra
    -0.07
    utow
    -0.06
    776
    -0.06
     Hop
    -0.06
    å½
    -0.06
     diagon
    -0.06
    _PENDING
    -0.06
    TPL
    -0.06
     PROGMEM
    -0.06
    POSITIVE LOGITS
    ropolis
    0.09
     fate
    0.08
     resistance
    0.08
    ordion
    0.07
    _requirements
    0.07
    ioned
    0.07
    atars
    0.07
     Meetings
    0.07
    oble
    0.06
     deadlines
    0.06
    Activations Density 0.022%

    No Known Activations