© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 19-LLAMASCOPE-RES-32K
    6. 28809
    Prev
    Next
    INDEX
    Explanations

    references to humanitarian crises and food insecurity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olia
    -0.17
    Stencil
    -0.17
    ensch
    -0.16
    -fi
    -0.16
    roma
    -0.15
     Ïĩα
    -0.14
    _Native
    -0.14
     Blasio
    -0.14
    alian
    -0.14
    rrha
    -0.13
    POSITIVE LOGITS
     food
    0.24
     famine
    0.24
     starvation
    0.23
     nutrition
    0.23
    -food
    0.21
     голод
    0.21
     hunger
    0.21
     feed
    0.21
    feed
    0.20
    /star
    0.20
    Activations Density 0.051%

    No Known Activations