INDEX

Explanations

numerical values, particularly in monetary contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

umba

-0.16

ena

-0.14

ylie

-0.14

ysl

-0.14

rov

-0.14

.Hosting

-0.14

caff

-0.14

 Optionally

-0.14

ÏĥÏĦÎ¬

-0.13

'field

-0.13

POSITIVE LOGITS

éĹª

0.16

shi

0.15

elmet

0.15

osen

0.14

 Favor

0.14

Age

0.14

rage

0.14

Ð°Ð»Ñĥ

0.14

iggers

0.13

AGE

0.13

Activations Density 0.050%

numerical values, particularly in monetary contexts

No Comments

No Known Activations