INDEX

Explanations

keywords and identifiers related to programming or coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ëĭ¤ìļ´ë°Ľê¸°

-0.17

rende

-0.15

 extr

-0.14

HCI

-0.14

porto

-0.13

 duly

-0.13

AWS

-0.13

 Ring

-0.13

 pazar

-0.13

.googleapis

-0.13

POSITIVE LOGITS

ByPrimaryKey

0.26

mapper

0.26

.ibatis

0.25

 addCriterion

0.25

 mapper

0.25

 sqlSession

0.23

Mapper

0.21

Selective

0.21

 Mapper

0.21

sql

0.21

Activations Density 0.002%

keywords and identifiers related to programming or coding

No Comments

No Known Activations