INDEX

Explanations

specific names or terms associated with a variety of cultural references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ops

-0.16

rod

-0.15

-0.14

cast

-0.14

elf

-0.13

ff

-0.13

Ð¾Ð¿Ð¾Ð»

-0.13

Die

-0.13

amat

-0.13

POSITIVE LOGITS

igy

0.16

ahlen

0.15

zÃŃ

0.15

æ´Ĺ

0.14

bury

0.14

Ð·Ñĸ

0.14

enser

0.14

emark

0.13

!=(

0.13

.selenium

0.13

Activations Density 0.021%

specific names or terms associated with a variety of cultural references

No Comments

No Known Activations