INDEX

Explanations

anticipatory phrases and intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oth

-0.15

 ÙĩÙħÚĨÙĨÛĮÙĨ

-0.14

ServletRequest

-0.14

 embar

-0.14

exion

-0.14

itta

-0.14

_INCLUDED

-0.13

~(

-0.13

ÐµÑĤÐµ

-0.13

rete

-0.13

POSITIVE LOGITS

too

0.97

too

0.85

Too

0.80

Too

0.76

TOO

0.73

-too

0.64

å¤ª

0.59

 demasi

0.55

 ÑģÐ»Ð¸ÑĪÐºÐ¾Ð¼

0.52

 å¤ª

0.45

Activations Density 0.109%

anticipatory phrases and intentions

No Comments

No Known Activations