© 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. 5-LLAMASCOPE-RES-131K
    11. 126148
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that indicate relationships or comparisons in discourse

    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
    akat
    -0.07
    TemplateName
    -0.07
    DONE
    -0.07
    GO
    -0.06
    allo
    -0.06
    Boom
    -0.06
    nz
    -0.06
    aron
    -0.06
    ais
    -0.06
    çµ
    -0.06
    POSITIVE LOGITS
    infeld
    0.07
    ä½ı
    0.07
    -Compatible
    0.07
    ency
    0.06
    ем
    0.06
    ÙĪÛĮÙĦ
    0.06
     stay
    0.06
    ottes
    0.06
    ãĥĥãĥģ
    0.06
     Wein
    0.06
    Activations Density 0.081%

    No Known Activations