INDEX

Explanations

different forms of the word "screening" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oya

-0.17

ucch

-0.15

 circular

-0.15

udev

-0.15

asca

-0.14

.MATCH

-0.14

å¨ĺ

-0.14

.habbo

-0.14

abet

-0.14

POSITIVE LOGITS

 Slater

0.16

ÅĻi

0.15

shade

0.15

utz

0.14

eing

0.14

ierz

0.14

å¹ķ

0.14

enzie

0.14

Ø¢Ùħ

0.14

ë¡

0.14

Activations Density 0.012%

different forms of the word "screening" and related terms

No Comments

No Known Activations