INDEX

Explanations

instances of news articles mentioning significant events or appearances related to media releases and announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

à¥ģà¤Ń

-0.15

sho

-0.15

 next

-0.14

urga

-0.14

 Gest

-0.14

Äĥm

-0.13

ieu

-0.13

stroy

-0.13

atha

-0.13

enga

-0.13

POSITIVE LOGITS

UBLE

0.17

mess

0.16

 èį

0.15

jis

0.15

atables

0.15

weet

0.14

hek

0.14

aram

0.14

ÏĨÎ±Ïģ

0.14

éĽĦ

0.13

Activations Density 0.182%

instances of news articles mentioning significant events or appearances related to media releases and announcements

No Comments

No Known Activations