INDEX

Explanations

terms related to various forms of media and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 latter

-0.37

/her

-0.19

EGIN

-0.18

âĢĲ

-0.18

deaux

-0.17

agua

-0.17

UGIN

-0.17

ses

-0.17

phans

-0.16

âĤ¬“

-0.16

POSITIVE LOGITS

/-

0.48

odore

0.27

gether

0.25

atre

0.23

adays

0.23

ern

0.22

ir

0.21

edly

0.19

enticator

0.19

ÑįÑĤÐ¾Ð¼Ñĥ

0.19

Activations Density 0.766%

terms related to various forms of media and entertainment

No Comments

No Known Activations