© 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. 19500
    Prev
    Next
    INDEX
    Explanations

    online resources and services related to academic assistance and e-commerce

    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
     Jub
    -0.16
    uala
    -0.14
    аÑĢÑĩ
    -0.14
    orris
    -0.14
    ýn
    -0.14
    HORT
    -0.13
    .ListBox
    -0.13
    mere
    -0.13
    PCODE
    -0.13
    ombine
    -0.13
    POSITIVE LOGITS
    .com
    0.69
    .org
    0.55
    .COM
    0.50
    .net
    0.49
    .co
    0.43
    .Com
    0.39
    .ca
    0.36
    .gov
    0.35
    .eu
    0.35
    .info
    0.34
    Activations Density 0.208%

    No Known Activations