INDEX

Explanations

programming commands related to data visualization and manipulation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enthal

-0.17

 squeeze

-0.15

uch

-0.14

 McCorm

-0.14

 circular

-0.14

adro

-0.14

marker

-0.13

{:

-0.13

Deferred

-0.13

 enrolled

-0.13

POSITIVE LOGITS

 library

0.19

_library

0.18

library

0.17

0.16

 libraries

0.15

odel

0.15

itesse

0.15

ãĥ©ãĤ¹

0.15

 çī

0.14

pun

0.14

Activations Density 0.020%

programming commands related to data visualization and manipulation

No Comments

No Known Activations