INDEX

Explanations

instances of the word "added" and related phrases indicating additional information or commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ze

-0.15

ild

-0.14

quez

-0.14

istrovstvÃŃ

-0.14

obre

-0.13

achi

-0.13

lav

-0.13

 McGr

-0.13

POSITIVE LOGITS

endum

0.20

 Latter

0.16

.gwt

0.15

istrar

0.14

å¸

0.14

note

0.14

 momentum

0.14

igham

0.14

endale

0.14

/gtest

0.14

Activations Density 0.014%

instances of the word "added" and related phrases indicating additional information or commentary

No Comments

No Known Activations