INDEX

Explanations

verbs that imply caution or action

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

unto

-0.15

emas

-0.15

 Elemental

-0.14

="__

-0.14

ìĭĿ

-0.14

/generated

-0.14

Ø¨Ø§ÙĨ

-0.14

.struct

-0.13

pliant

-0.13

 Cald

-0.13

POSITIVE LOGITS

igham

0.14

isu

0.14

 accordingly

0.13

icha

0.13

habi

0.13

ÃŃl

0.13

 Burl

0.13

-↵

0.13

.fixture

0.13

Activations Density 0.206%

verbs that imply caution or action

No Comments

No Known Activations