© 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. 18-LLAMASCOPE-RES-32K
    11. 2265
    Prev
    Next
    INDEX
    Explanations

    references to misuse or misallocation of funds and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     æ°
    -0.15
     bil
    -0.14
    apper
    -0.13
     terk
    -0.13
    812
    -0.13
    ì°©
    -0.13
     queryInterface
    -0.13
    /options
    -0.13
    abo
    -0.13
    arc
    -0.13
    POSITIVE LOGITS
     purposes
    0.56
     purpose
    0.52
    purpose
    0.46
     Purpose
    0.41
    Purpose
    0.40
     PURPOSE
    0.40
    -purpose
    0.40
    缮çļĦ
    0.36
     intended
    0.33
    urpose
    0.33
    Activations Density 0.178%

    No Known Activations