INDEX

Explanations

words related to entertainment or media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

cher

-0.17

-0.16

 status

-0.16

oice

-0.15

kle

-0.15

am

-0.15

.cgi

-0.15

DM

-0.14

unct

-0.14

mem

-0.14

POSITIVE LOGITS

ÌĨ

0.15

/Set

0.15

ernes

0.15

oftware

0.15

ÑģÑĤÐ¸

0.14

-Version

0.14

OrNil

0.14

ellen

0.14

TZ

0.14

ylie

0.14

Activations Density 0.000%

words related to entertainment or media

No Comments

No Known Activations