INDEX

Explanations

references to pharmaceutical products or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ð¼Ð¸Ð½Ð¸

-0.17

ijd

-0.17

ards

-0.16

ÏĦÎ®

-0.15

ungan

-0.14

kees

-0.14

abelle

-0.14

µ¬

-0.14

Wel

-0.14

æ¼

-0.14

POSITIVE LOGITS

osph

0.22

Ph

0.22

OTOS

0.22

ph

0.22

araoh

0.21

ases

0.21

ishing

0.20

oe

0.19

thal

0.19

oen

0.19

Activations Density 0.021%

references to pharmaceutical products or related concepts

No Comments

No Known Activations