INDEX

Explanations

components related to academic article structure and formatting

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

umber

-0.19

umper

-0.15

yc

-0.14

èµı

-0.13

.snap

-0.13

omain

-0.13

ç¯ĩ

-0.13

ãģĵãģ¡ãĤī

-0.13

.Sdk

-0.13

ominator

-0.13

POSITIVE LOGITS

adil

0.19

ilos

0.15

.Factory

0.15

abal

0.14

iller

0.14

Mam

0.14

kav

0.14

å®Ļ

0.14

raham

0.13

EDIA

0.13

Activations Density 0.003%

components related to academic article structure and formatting

No Comments

No Known Activations