© 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. 71250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" and its associated phrases indicating purposes or reasons

    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
    onn
    -0.07
    hurst
    -0.07
    _ISR
    -0.07
    ãĤ¿ãĥ¼
    -0.07
    typed
    -0.07
    oes
    -0.07
     sanat
    -0.07
    _numer
    -0.07
    ottage
    -0.07
    instanc
    -0.07
    POSITIVE LOGITS
     roles
    0.06
    emaker
    0.06
     success
    0.06
    atore
    0.06
    sti
    0.06
     inclusion
    0.06
    merc
    0.06
     consideration
    0.06
    &
    0.06
    670
    0.05
    Activations Density 0.024%

    No Known Activations