© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119387
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contradictions or problems in narratives

    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
     maybe
    -0.06
    estone
    -0.06
     may
    -0.06
     unh
    -0.06
     or
    -0.06
     unmanned
    -0.05
    isz
    -0.05
    479
    -0.05
     Err
    -0.05
     box
    -0.05
    POSITIVE LOGITS
    åĢ«
    0.08
    _startup
    0.08
    INY
    0.08
    .parameters
    0.07
    ANGO
    0.07
     миÑĤ
    0.07
    ortal
    0.07
     Kültür
    0.07
     forensic
    0.07
    Ø´ÙħاÙĦÛĮ
    0.07
    Activations Density 0.001%

    No Known Activations