© 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. 84515
    Prev
    Next
    INDEX
    Explanations

    occurrences of conjunctions and transitions in the text

    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
    оÑĢони
    -0.07
    ardown
    -0.07
    avo
    -0.07
    ómo
    -0.07
     putas
    -0.07
     fisse
    -0.07
    .tc
    -0.07
    afort
    -0.07
    ctl
    -0.07
    gnore
    -0.07
    POSITIVE LOGITS
     when
    0.20
    when
    0.17
     whenever
    0.17
     cuando
    0.15
     quando
    0.15
     When
    0.14
    When
    0.14
    _when
    0.14
     WHEN
    0.13
     когда
    0.13
    Activations Density 0.107%

    No Known Activations