INDEX

Explanations

proper nouns associated with sports, literature, and notable individuals

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

istrovstvÃŃ

-0.23

atrix

-0.16

isphere

-0.15

elijke

-0.15

Ú¯Ø±

-0.15

caffold

-0.14

hta

-0.14

pered

-0.13

PERT

-0.13

alim

-0.13

POSITIVE LOGITS

mente

0.23

ities

0.17

most

0.17

zeitig

0.16

omore

0.16

acre

0.15

-ÑĤÐ°ÐºÐ¸

0.15

ëª»

0.15

éĥ

0.15

/fast

0.15

Activations Density 0.460%

proper nouns associated with sports, literature, and notable individuals

No Comments

No Known Activations