INDEX

Explanations

phrases that indicate uncertainty or potential changes in circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ø·Ø±

-0.15

aller

-0.15

ä¹Ĺ

-0.15

atar

-0.14

berger

-0.14

ick

-0.14

Ø¬Ø±

-0.14

ë·

-0.14

 Cold

-0.14

 rewriting

-0.14

POSITIVE LOGITS

opor

0.17

.opend

0.15

ventions

0.15

 actual

0.14

sth

0.14

-ignore

0.14

×ķ

0.14

actual

0.14

oire

0.14

stal

0.14

Activations Density 0.087%

phrases that indicate uncertainty or potential changes in circumstances

No Comments

No Known Activations