© 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. 87675
    Prev
    Next
    INDEX
    Explanations

    references to regulatory goals and programs related to waste management

    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
    https
    -0.06
     -
    -0.06
     &
    -0.06
     spatial
    -0.06
    avig
    -0.06
    ::
    -0.06
     –
    -0.06
     variables
    -0.05
    -0.05
    icc
    -0.05
    POSITIVE LOGITS
    ÑģÑĭ
    0.08
    lesia
    0.07
    inaire
    0.07
    .useState
    0.07
     Engineer
    0.07
    Â
    0.07
     Cure
    0.07
     performan
    0.07
     Rica
    0.07
    .bunifuFlatButton
    0.07
    Activations Density 0.002%

    No Known Activations