INDEX

Explanations

components related to configuration or definition in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

laden

-0.15

 Conrad

-0.15

allee

-0.14

mund

-0.14

uko

-0.14

etine

-0.14

_guard

-0.14

edy

-0.13

gÄ±n

-0.13

 Ø¯ÙĨØ¨Ø§ÙĦ

-0.13

POSITIVE LOGITS

apos

0.16

ÂĿ

0.15

0.14

adle

0.14

ãĤ§

0.14

mp

0.14

Ð¾Ð»ÑĮÐºÑĥ

0.13

.AddComponent

0.13

Activations Density 0.041%

components related to configuration or definition in code

No Comments

No Known Activations