INDEX

Explanations

phrases indicating past experiences or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ð°ÑĤÐºÑĥ

-0.15

-ves

-0.14

elf

-0.14

è«¾

-0.13

-xl

-0.13

.tm

-0.13

not

-0.13

hum

-0.13

POSITIVE LOGITS

opher

0.18

urette

0.16

lege

0.15

Î¼Î¿Î¯

0.14

uide

0.14

issen

0.14

orgen

0.14

Pv

0.14

neau

0.14

 both

0.13

Activations Density 0.048%

phrases indicating past experiences or conditions

No Comments

No Known Activations