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

    Neuronpedia

    Jacobian LensNEW
    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. 18-LLAMASCOPE-RES-32K
    11. 22379
    Prev
    Next
    INDEX
    Explanations

    themes of compassion and support for vulnerable groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    301
    -0.14
    plode
    -0.14
    IRR
    -0.14
    878
    -0.14
    acher
    -0.14
    ÏĦε
    -0.14
    loh
    -0.13
    eyin
    -0.13
    ÅĻe
    -0.13
     bloodstream
    -0.13
    POSITIVE LOGITS
     vulnerable
    0.23
     neglected
    0.19
     poor
    0.18
     populations
    0.18
     children
    0.17
     defense
    0.17
     victims
    0.17
     homeless
    0.16
     exploited
    0.16
     innoc
    0.16
    Activations Density 0.201%

    No Known Activations