© 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. 126021
    Prev
    Next
    INDEX
    Explanations

    terms related to water pollution and regulatory frameworks

    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
     Howard
    -0.06
    iana
    -0.06
    assis
    -0.06
    aret
    -0.06
    Howard
    -0.06
    arch
    -0.06
     Chancellor
    -0.06
     sec
    -0.06
    artial
    -0.05
    artz
    -0.05
    POSITIVE LOGITS
    lý
    0.08
    _hook
    0.08
    ozy
    0.07
    žen
    0.07
    ?action
    0.07
    owi
    0.07
    Ascii
    0.07
    _hooks
    0.07
    -hooks
    0.07
    iplinary
    0.07
    Activations Density 0.013%

    No Known Activations