INDEX

Explanations

phrases related to the concept of access and limitations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

istributed

-0.19

 Batch

-0.16

duk

-0.15

erif

-0.15

Ð¸ÑĤÐµÑĤ

-0.15

Batch

-0.14

 BATCH

-0.14

 rallies

-0.14

.emf

-0.14

/Area

-0.14

POSITIVE LOGITS

 scenes

0.19

 bounds

0.18

 veil

0.18

 ÙħØ¨Ø§Ø´

0.17

wert

0.17

-scenes

0.17

 confines

0.16

 threshold

0.16

ones

0.15

_KEYBOARD

0.15

Activations Density 0.072%

phrases related to the concept of access and limitations in various contexts

No Comments

No Known Activations