INDEX

Explanations

references to physical spaces and distances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.weixin

-0.16

´Ī

-0.16

 (*((

-0.16

AGMA

-0.15

ector

-0.15

nar

-0.15

Î´Î·

-0.14

Ø§Ø®

-0.14

richt

-0.14

nett

-0.14

POSITIVE LOGITS

kit

0.17

argin

0.17

Kit

0.16

oy

0.16

 negoci

0.15

ilog

0.15

0.14

į¼

0.14

_sibling

0.14

Activations Density 0.246%

references to physical spaces and distances

No Comments

No Known Activations