INDEX

Explanations

percentages and statistical data references

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

 Warfare

-0.15

avirus

-0.15

.Clock

-0.15

enthal

-0.14

ugar

-0.14

ISMATCH

-0.14

 bare

-0.14

lore

-0.14

aled

-0.14

POSITIVE LOGITS

 Doub

0.15

.appspot

0.15

 Plus

0.14

iale

0.14

ppers

0.14

 expense

0.14

ernet

0.14

rou

0.14

ecess

0.13

YG

0.13

Activations Density 0.059%

percentages and statistical data references

No Comments

No Known Activations