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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7684
    Prev
    Next
    INDEX
    Explanations

    phrases related to balance and variety

    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
    olas
    -0.16
    onis
    -0.15
    vault
    -0.15
    ksen
    -0.15
    sted
    -0.15
    ÏģοÏħ
    -0.14
    .localization
    -0.14
    oleÄį
    -0.14
    ceil
    -0.13
    .ceil
    -0.13
    POSITIVE LOGITS
     intermediate
    0.78
     Intermediate
    0.67
    Intermediate
    0.64
     intermediary
    0.62
     middle
    0.60
     intermedi
    0.59
    middle
    0.50
     intervening
    0.50
     between
    0.49
    ä¸Ń
    0.47
    Activations Density 0.200%

    No Known Activations