INDEX

Explanations

phrases indicating implications or considerations for a group or subject

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

uet

-0.15

netinet

-0.14

etter

-0.14

/rfc

-0.14

 Kerr

-0.14

 Cocktail

-0.14

å¥ı

-0.14

amer

-0.14

INGTON

-0.14

esse

-0.14

POSITIVE LOGITS

 Loose

0.16

ImageButton

0.16

reira

0.16

 loose

0.15

ÙİØ§ÙĨ

0.15

IED

0.14

TOTYPE

0.14

ImagePath

0.14

ike

0.14

Activations Density 0.030%

phrases indicating implications or considerations for a group or subject

No Comments

No Known Activations