© 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. 71426
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and moral responsibility in tense situations

    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
    byn
    -0.08
    ephy
    -0.07
    é»
    -0.07
    venge
    -0.07
    zik
    -0.06
    hai
    -0.06
    CLI
    -0.06
    ophobia
    -0.06
    isky
    -0.06
    ekil
    -0.06
    POSITIVE LOGITS
     capture
    0.09
    capture
    0.08
     Capture
    0.08
     disarm
    0.07
    Capture
    0.07
     unarmed
    0.07
    _NET
    0.07
     captures
    0.07
     surrender
    0.06
    _capture
    0.06
    Activations Density 0.047%

    No Known Activations