INDEX

Explanations

geographic locations, specifically states in the U.S. and countries

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

 trang

-0.15

elin

-0.14

oxy

-0.14

uib

-0.14

ych

-0.14

ķìĿ¸

-0.14

ardu

-0.13

\grid

-0.13

UDO

-0.13

ÏĢÎ¿

-0.13

POSITIVE LOGITS

PFN

0.15

tiler

0.14

 Narr

0.14

Ã¼stÃ¼

0.14

-alist

0.14

OOM

0.14

 organisers

0.14

 recep

0.13

Activations Density 0.026%

geographic locations, specifically states in the U.S. and countries

No Comments

No Known Activations