INDEX

Explanations

specific patterns or characters that indicate non-Latin scripts or encoded text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

azÄĥ

-0.16

enko

-0.15

lox

-0.15

ava

-0.15

Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

-0.14

.defaults

-0.14

TestFixture

-0.14

bes

-0.14

ÅĽÄĩ

-0.14

lanmÄ±ÅŁ

-0.14

POSITIVE LOGITS

_hdl

0.16

ual

0.15

mighty

0.14

ylan

0.14

ush

0.14

Ø³Ø·Ø³

0.14

aes

0.14

AAD

0.14

=A

0.14

itm

0.13

Activations Density 0.059%

specific patterns or characters that indicate non-Latin scripts or encoded text

No Comments

No Known Activations