INDEX

Explanations

numerical values related to participants and time in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ino

-0.15

nod

-0.14

rg

-0.14

ãĤ¤ãĤº

-0.14

avia

-0.14

 Angus

-0.14

 Shaw

-0.13

gam

-0.13

projection

-0.13

.quick

-0.13

POSITIVE LOGITS

erus

0.17

elsen

0.17

retch

0.15

igidBody

0.15

asticsearch

0.14

Smarty

0.14

zahl

0.14

Opera

0.14

uisine

0.14

ossa

0.13

Activations Density 0.052%

numerical values related to participants and time in various contexts

No Comments

No Known Activations