INDEX

Explanations

questions and discussions about future events or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

chez

-0.18

vecs

-0.16

ething

-0.15

 Albert

-0.15

svp

-0.14

PerPixel

-0.14

ITED

-0.14

ropdown

-0.14

icer

-0.14

acles

-0.14

POSITIVE LOGITS

 when

0.16

/how

0.16

imb

0.16

 nÃ¤r

0.15

 after

0.14

	when

0.14

Ã¡d

0.14

lore

0.14

 dopo

0.14

 OPTIONS

0.14

Activations Density 0.100%

questions and discussions about future events or outcomes

No Comments

No Known Activations