INDEX

Explanations

terms related to boolean data types and boolean logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

gaard

-0.16

èİ«

-0.15

gae

-0.15

Å¡e

-0.14

-degree

-0.14

.soft

-0.14

ection

-0.14

ç¹ģ

-0.14

uled

-0.14

 Manson

-0.14

POSITIVE LOGITS

hma

0.16

urray

0.15

ìĬµ

0.15

ffield

0.15

Ala

0.15

ought

0.14

ys

0.14

ento

0.14

 Maver

0.14

Activations Density 0.015%

terms related to boolean data types and boolean logic

No Comments

No Known Activations