INDEX

Explanations

programming concepts and coding related instructions

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

togroup

-0.15

ydk

-0.15

 RuntimeObject

-0.15

logg

-0.15

.mybatisplus

-0.14

-eslint

-0.14

_ATTACH

-0.14

\Blueprint

-0.14

hes

-0.13

cherche

-0.13

POSITIVE LOGITS

 server

0.28

 client

0.28

 browser

0.26

 clients

0.25

 brow

0.22

 requests

0.22

 Client

0.22

 request

0.22

 served

0.22

 Ajax

0.22

Activations Density 0.060%

programming concepts and coding related instructions

No Comments

No Known Activations