INDEX

Explanations

references to groups, organizations, or partnerships in business contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Quit

-0.15

 Myers

-0.14

ATAB

-0.14

rones

-0.14

avl

-0.13

Ð³Ð»

-0.13

atitis

-0.13

 taper

-0.13

wie

-0.13

mag

-0.13

POSITIVE LOGITS

owned

0.23

 owned

0.20

Owned

0.16

ingroup

0.16

tron

0.15

belongs

0.15

 parent

0.15

parent

0.15

ä¸ĺ

0.15

èĬĿ

0.15

Activations Density 0.062%

references to groups, organizations, or partnerships in business contexts

No Comments

No Known Activations