© 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. 57545
    Prev
    Next
    INDEX
    Explanations

    references to direct communication and engagement with audiences

    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
    uru
    -0.06
    wang
    -0.06
    ets
    -0.06
     Kov
    -0.06
    ooter
    -0.06
    uhn
    -0.06
    eful
    -0.06
     CO
    -0.06
    ossip
    -0.06
    unate
    -0.06
    POSITIVE LOGITS
     direct
    0.17
     directly
    0.16
    direct
    0.15
    Direct
    0.15
     Direct
    0.14
    缴æİ¥
    0.13
    _direct
    0.13
    .direct
    0.12
     interaction
    0.12
     DIRECT
    0.12
    Activations Density 0.084%

    No Known Activations