INDEX

Explanations

words and phrases related to entertainment and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÌĨ

-0.17

adius

-0.16

OND

-0.15

ely

-0.15

ãĥĨãĥ«

-0.14

ctor

-0.14

ulla

-0.14

trand

-0.14

eliness

-0.14

POSITIVE LOGITS

ertainment

0.25

ropic

0.23

_QUOTES

0.22

rench

0.22

itled

0.21

angled

0.19

ourage

0.19

ent

0.19

ebe

0.18

ailed

0.18

Activations Density 0.010%

words and phrases related to entertainment and media

No Comments

No Known Activations