INDEX

Explanations

statements and actions related to company announcements and reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

quential

-0.16

malink

-0.15

Č

-0.15

ãĤ¦ãĥĪ

-0.14

Dit

-0.14

ermen

-0.13

íĥĿ

-0.13

Ð°Ð»ÐµÐ¶

-0.13

Ð¾Ð±ÑĢÐ°Ð·

-0.13

OLLOW

-0.13

POSITIVE LOGITS

jer

0.15

0.14

edn

0.13

obre

0.13

onda

0.13

alles

0.13

ripp

0.13

à¸±à¸ģà¸ģ

0.12

hq

0.12

ITU

0.12

Activations Density 0.265%

statements and actions related to company announcements and reports

No Comments

No Known Activations