© 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. 22-LLAMASCOPE-RES-32K
    6. 21177
    Prev
    Next
    INDEX
    Explanations

    topics related to food security and hunger issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dosage
    -0.15
    ymoon
    -0.14
    ativa
    -0.14
    ยะ
    -0.14
    idade
    -0.14
     launder
    -0.13
    rip
    -0.13
    667
    -0.13
     Doch
    -0.13
     sanit
    -0.13
    POSITIVE LOGITS
     food
    0.52
     hunger
    0.49
     hungry
    0.43
    food
    0.42
    -food
    0.42
     Food
    0.40
     Hunger
    0.40
     starvation
    0.39
    Food
    0.39
     FOOD
    0.39
    Activations Density 0.173%

    No Known Activations