INDEX

Explanations

content related to personal identity and professional background 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ð

-0.16

ï¼ĭ

-0.15

âĻ¡

-0.15

ãħł

-0.14

 INTERRU

-0.14

 Ticaret

-0.14

#echo

-0.14

JNI

-0.13

umni

-0.13

undler

-0.13

POSITIVE LOGITS

0.16

 Elder

0.15

amp

0.14

 [âĢ¦]↵

0.14

The

0.14

cheid

0.14

ï

0.13

ail

0.13

anan

0.13

Activations Density 0.047%

content related to personal identity and professional background in various contexts

No Comments

No Known Activations