INDEX

Explanations

indicators of remembrance and legacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.14

caffold

-0.14

aycast

-0.14

elpers

-0.14

.files

-0.13

 suspicious

-0.13

 ÑģÑħÐ¾Ð´

-0.13

 ########.

-0.13

POSITIVE LOGITS

 testimony

0.34

 symbol

0.34

 statement

0.31

 representation

0.31

 testament

0.30

 reminder

0.30

symbol

0.27

 sign

0.27

 tribute

0.27

 expression

0.27

Activations Density 0.220%

indicators of remembrance and legacy

No Comments

No Known Activations