INDEX

Explanations

instances where the text encourages the reader to access additional information or content

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

edImage

-0.15

uÄį

-0.15

deo

-0.15

éĩĳ

-0.14

igi

-0.14

dy

-0.14

å·Ŀ

-0.14

bin

-0.14

yles

-0.13

bus

-0.13

POSITIVE LOGITS

UBLE

0.20

.experimental

0.17

ungle

0.15

.cx

0.15

cts

0.15

_runner

0.15

acd

0.14

omik

0.14

åľ

0.14

oid

0.14

Activations Density 0.106%

instances where the text encourages the reader to access additional information or content

No Comments

No Known Activations