INDEX

Explanations

dates and numeric information within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

immer

-0.15

ODO

-0.14

olt

-0.14

eners

-0.14

elson

-0.14

.Html

-0.14

rossover

-0.14

gate

-0.13

 Tradition

-0.13

ucson

-0.13

POSITIVE LOGITS

wig

0.19

etur

0.18

PR

0.16

PR

0.15

upakan

0.15

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.14

ãĥ¼ãĥĨ

0.14

ãĥ¼ãĤ¹ãĥĪ

0.14

Pry

0.14

LS

0.14

Activations Density 0.008%

dates and numeric information within the text

No Comments

No Known Activations