INDEX

Explanations

programming-related technical terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

neau

-0.17

imon

-0.16

azi

-0.15

ctor

-0.15

ynet

-0.14

ĮĢ

-0.14

 Conc

-0.14

uci

-0.14

CLR

-0.14

POSITIVE LOGITS

bah

0.16

isse

0.15

lÃŃn

0.15

.metro

0.14

 subrange

0.14

ĵĺ

0.14

ABCDEFGHI

0.13

ilege

0.13

Gel

0.13

yen

0.13

Activations Density 0.218%

programming-related technical terms and concepts

No Comments

No Known Activations