INDEX

Explanations

technical terms related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

rende

-0.17

ìłĪ

-0.16

.volley

-0.15

.resolution

-0.15

/assert

-0.14

iske

-0.14

ovat

-0.13

 decoration

-0.13

resar

-0.13

 ÐļÐ¾ÑģÑĤ

-0.13

POSITIVE LOGITS

ross

0.19

McL

0.16

ijing

0.16

chal

0.14

Ø¹ÛĮ

0.14

rawn

0.14

venture

0.14

tan

0.14

chemes

0.14

amar

0.13

Activations Density 0.100%

technical terms related to programming and data structures

No Comments

No Known Activations