INDEX

Explanations

phrases that convey routine or common occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

emer

-0.17

oral

-0.17

ussen

-0.16

ikal

-0.15

å§ĭ

-0.15

ÐµÑģÑĮ

-0.15

à¥Ģà¤¯

-0.15

buz

-0.14

ager

-0.14

POSITIVE LOGITS

ty

0.20

mente

0.19

ties

0.18

ities

0.18

Ù

0.18

 suspects

0.18

/common

0.17

AYOUT

0.17

ndef

0.16

ÌĨ

0.16

Activations Density 0.020%

phrases that convey routine or common occurrences

No Comments

No Known Activations