INDEX

Explanations

references to government bodies and their officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

igo

-0.18

orus

-0.16

æīİ

-0.15

olet

-0.15

ãģĳãģªãģĦ

-0.15

igos

-0.15

º

-0.14

anity

-0.14

Arm

-0.14

POSITIVE LOGITS

awn

0.15

ylie

0.15

0.14

atform

0.14

elan

0.14

 Ã¼y

0.14

arie

0.14

Wo

0.13

 Grove

0.13

gom

0.13

Activations Density 0.212%

references to government bodies and their officials

No Comments

No Known Activations