INDEX

Explanations

actions and movements described in dynamic or physical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

undy

-0.15

itre

-0.15

igo

-0.15

ãĥĥãĥĦ

-0.15

trace

-0.14

ä¹ĭä¸Ģ

-0.14

stasy

-0.14

.rs

-0.13

 Russo

-0.13

opus

-0.13

POSITIVE LOGITS

 into

0.24

 forth

0.23

 away

0.23

into

0.18

away

0.16

 past

0.16

off

0.16

 Away

0.16

 toward

0.16

ingly

0.16

Activations Density 0.090%

actions and movements described in dynamic or physical terms

No Comments

No Known Activations