INDEX

Explanations

phrases related to the concept of danger or risk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

operand

-0.17

tile

-0.15

andum

-0.15

anga

-0.14

igel

-0.13

mile

-0.13

 Dess

-0.13

ondo

-0.13

Ã¨s

-0.13

OOT

-0.13

POSITIVE LOGITS

ÌĨ

0.20

Ìģ

0.17

Ì

0.17

ÙĤØ§Øª

0.15

ull

0.15

arken

0.15

lington

0.14

ÌĪ

0.14

****************************************************************************

0.14

loe

0.14

Activations Density 2.156%

phrases related to the concept of danger or risk

No Comments

No Known Activations