© 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. 15-LLAMASCOPE-RES-131K
    11. 61883
    Prev
    Next
    INDEX
    Explanations

    references to policies related to family leave programs

    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
     chatt
    -0.07
     ViewState
    -0.06
     buc
    -0.06
    нÑĤ
    -0.06
    Ïħμ
    -0.06
    çĬ¶
    -0.06
     Choi
    -0.06
    otti
    -0.06
    ocz
    -0.06
    _fsm
    -0.06
    POSITIVE LOGITS
    aggio
    0.07
     bills
    0.06
     ninh
    0.06
    childs
    0.06
    estroy
    0.06
    ³
    0.06
    олÑĮ
    0.06
    553
    0.06
     items
    0.05
     House
    0.05
    Activations Density 0.001%

    No Known Activations