INDEX

Explanations

terms related to the concept of meaning and its interpretation

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

minster

-0.19

gate

-0.17

Ø³ØªØ§ÙĨ

-0.17

/lists

-0.15

oÅĪ

-0.14

apult

-0.14

bery

-0.14

BaseContext

-0.14

POSITIVE LOGITS

fully

0.21

ful

0.21

FUL

0.19

nes

0.18

/sign

0.17

nest

0.17

 meaning

0.17

ìĹ´

0.16

iful

0.15

cen

0.15

Activations Density 0.044%

terms related to the concept of meaning and its interpretation

No Comments

No Known Activations