INDEX

Explanations

words and phrases related to health issues and environmental assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ready

-0.15

erra

-0.14

oÅĪ

-0.13

byss

-0.13

itzer

-0.13

 versa

-0.13

RelativeTo

-0.13

enn

-0.12

 Wald

-0.12

POSITIVE LOGITS

urat

0.16

ÐºÐ¾Ð¿

0.15

urb

0.15

ovich

0.14

ssi

0.14

matic

0.14

arlo

0.14

raphic

0.14

olle

0.14

 Devils

0.14

Activations Density 0.146%

words and phrases related to health issues and environmental assessments

No Comments

No Known Activations