INDEX

Explanations

words and phrases related to product features and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

æĴ

-0.17

ëĶ

-0.16

EMPL

-0.15

ÐµÐ²Ð¸

-0.15

å¢

-0.14

ÐµÑĢÐº

-0.14

ãĥĲãĥ¼

-0.14

.codes

-0.14

å»

-0.14

iginal

-0.14

POSITIVE LOGITS

 Boeh

0.15

 Brace

0.14

phas

0.14

asin

0.14

lt

0.14

Cmd

0.14

ocha

0.14

Wr

0.14

Beh

0.13

nj

0.13

Activations Density 0.482%

words and phrases related to product features and performance

No Comments

No Known Activations