© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56730
    Prev
    Next
    INDEX
    Explanations

    subject lines and status updates related to email communication and order processing

    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
    }elseif
    -0.07
    ç©´
    -0.07
     é¦
    -0.07
    ापन
    -0.06
    rib
    -0.06
    ÅĻÃŃz
    -0.06
     Bernstein
    -0.06
     nok
    -0.06
    ä¾į
    -0.06
    .rmi
    -0.06
    POSITIVE LOGITS
    417
    0.07
    ovah
    0.07
    enha
    0.06
     Harlem
    0.06
    itational
    0.06
     Attached
    0.06
     blah
    0.06
    μμ
    0.06
     Essentials
    0.06
     attached
    0.06
    Activations Density 0.007%

    No Known Activations