INDEX

Explanations

references to specific identifiers and classifications in data contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 vice

-0.15

ognitive

-0.14

ourt

-0.14

 impl

-0.14

upertino

-0.14

Rel

-0.13

ror

-0.13

Ð¸ÑģÑĮ

-0.13

owan

-0.13

ewan

-0.13

POSITIVE LOGITS

ISR

0.18

çłģ

0.17

inders

0.15

alaria

0.15

eros

0.15

UsingEncoding

0.15

utow

0.14

áºł

0.14

ghan

0.14

ignKey

0.14

Activations Density 0.167%

references to specific identifiers and classifications in data contexts

No Comments

No Known Activations