INDEX

Explanations

terms related to legal proceedings and obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

åīĽ

-0.18

-0.15

 homelessness

-0.15

beck

-0.15

 Trevor

-0.15

relevant

-0.15

 relevant

-0.14

 Ø§ÙĦØ®Ø§Øµ

-0.14

 dispute

-0.14

ÐµÑĪ

-0.14

POSITIVE LOGITS

 shall

0.20

 boobs

0.17

 Shall

0.16

ippy

0.16

shall

0.15

 embracing

0.15

"*

0.15

 liqu

0.15

 embraced

0.15

Aid

0.14

Activations Density 0.209%

terms related to legal proceedings and obligations

No Comments

No Known Activations