INDEX

Explanations

instances of high numerical values or important parameters in a structured document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Lynch

-0.15

ates

-0.15

ant

-0.14

st

-0.14

erm

-0.14

ocrats

-0.14

 gang

-0.14

ighest

-0.14

hood

-0.14

iami

-0.14

POSITIVE LOGITS

Verifier

0.14

 SUBSTITUTE

0.13

Ø´Ø§Ùĩ

0.13

etooth

0.13

onne

0.13

oled

0.13

vironment

0.13

ensored

0.13

_OBJC

0.13

ableOpacity

0.13

Activations Density 0.014%

instances of high numerical values or important parameters in a structured document

No Comments

No Known Activations