INDEX

Explanations

references to relationships and interactions between individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

allis

-0.16

 Merk

-0.15

adder

-0.14

ÄĽÅ¾

-0.14

oogle

-0.14

uros

-0.14

 Publications

-0.14

chi

-0.13

Ð¾Ð²Ð°ÑĢ

-0.13

ocard

-0.13

POSITIVE LOGITS

é¢

0.15

ahlen

0.14

McM

0.14

ival

0.14

ahas

0.14

 counterpart

0.14

/tutorial

0.14

igne

0.13

 counterparts

0.13

 Pend

0.13

Activations Density 0.190%

references to relationships and interactions between individuals or groups

No Comments

No Known Activations