INDEX

Explanations

words related to the concept of uncovering or disclosing information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

LEAN

-0.16

klad

-0.15

Ð»ÐºÐ¸

-0.15

ergus

-0.15

ÄįÃŃ

-0.14

INU

-0.14

 Cush

-0.14

åĲ¹

-0.14

ìĹħì²´

-0.14

.existsSync

-0.14

POSITIVE LOGITS

isp

0.15

inq

0.14

Ã³st

0.14

omatic

0.14

opl

0.14

apot

0.14

0.13

ital

0.13

Activations Density 0.064%

words related to the concept of uncovering or disclosing information

No Comments

No Known Activations