INDEX

Explanations

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Ð¼Ð°Ð³

-0.16

gfx

-0.16

 ifndef

-0.15

elong

-0.15

esson

-0.14

 Mile

-0.14

ennes

-0.14

 Saud

-0.14

assis

-0.14

OS

-0.14

POSITIVE LOGITS

chte

0.17

isyon

0.17

YNAM

0.16

.scalablytyped

0.15

uesta

0.14

lica

0.14

 jadx

0.14

ÐĤ

0.13

pta

0.13

.badlogic

0.13

Activations Density 0.069%

numerical data and statistics

No Comments

No Known Activations