INDEX

Explanations

references to a specific company or organizational entity and its policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 mattered

-0.13

è£ķ

-0.13

atham

-0.12

æĿ¥äºĨ

-0.12

$MESS

-0.12

WARDED

-0.12

rung

-0.12

Ð¾ÑĢÑĸÐ²

-0.12

ungle

-0.12

èĤ¯

-0.12

POSITIVE LOGITS

 reserves

0.44

 reserve

0.40

 shall

0.30

reserve

0.29

 hereby

0.28

 reserved

0.27

 expressly

0.25

 DISCLAIMS

0.25

 SHALL

0.25

 Reserve

0.24

Activations Density 0.094%

references to a specific company or organizational entity and its policies

No Comments

No Known Activations