© 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. 25-LLAMASCOPE-RES-32K
    11. 22162
    Prev
    Next
    INDEX
    Explanations

    concerns about public health and safety in relation to corporate influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agnost
    -0.17
    agma
    -0.15
    ewire
    -0.14
    islav
    -0.14
    ð
    -0.14
    име
    -0.14
    duit
    -0.14
     proced
    -0.14
    erti
    -0.14
    ecut
    -0.13
    POSITIVE LOGITS
     health
    0.33
     Epidemi
    0.31
     epidemi
    0.29
     Health
    0.29
     Public
    0.29
     public
    0.28
     MPH
    0.28
    health
    0.27
     Population
    0.27
    -health
    0.27
    Activations Density 0.149%

    No Known Activations