© 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. 24-LLAMASCOPE-RES-32K
    11. 8357
    Prev
    Next
    INDEX
    Explanations

    phrases related to socioeconomic issues and the struggles of vulnerable populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    locker
    -0.16
     coward
    -0.15
     деле
    -0.15
     Personnel
    -0.14
    ëĭ´
    -0.14
    βε
    -0.14
     ÄĮech
    -0.13
     overwritten
    -0.13
    uisse
    -0.13
    791
    -0.13
    POSITIVE LOGITS
     homeless
    0.40
     homelessness
    0.36
     poverty
    0.34
     dest
    0.32
     hunger
    0.30
     food
    0.30
     hungry
    0.27
     Poverty
    0.27
     basic
    0.25
    food
    0.23
    Activations Density 0.023%

    No Known Activations