INDEX

Explanations

phrases related to moving forward or transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ackers

-0.17

auty

-0.15

.unpack

-0.15

coop

-0.15

ibal

-0.15

ieties

-0.14

áº¯p

-0.14

ëĥ¥

-0.14

RowAt

-0.14

ãĥ¼ãĤ¹

-0.14

POSITIVE LOGITS

rig

0.16

isman

0.15

ifs

0.14

rig

0.14

rog

0.14

IFS

0.13

it

0.13

ÑĥÑģÐ°

0.13

 Watkins

0.13

 cons

0.13

Activations Density 0.017%

phrases related to moving forward or transitions

No Comments

No Known Activations