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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84163
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to obligations or expectations

    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
    atak
    -0.07
    keterangan
    -0.06
    ycl
    -0.06
    anity
    -0.06
     suất
    -0.06
    rawer
    -0.06
     Cout
    -0.06
    alace
    -0.06
    apper
    -0.06
     Jar
    -0.06
    POSITIVE LOGITS
    eld
    0.07
    ÏģÏħ
    0.07
     priorities
    0.06
    InView
    0.06
    -fw
    0.06
     NavParams
    0.06
    ispecies
    0.06
    tol
    0.06
     Inch
    0.06
    573
    0.06
    Activations Density 0.000%

    No Known Activations