INDEX

Explanations

phrases that indicate likelihood or probability regarding future events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Sometimes

-0.17

 olab

-0.17

hin

-0.16

sometimes

-0.16

 sometimes

-0.16

ometimes

-0.16

 occasionally

-0.15

ä¹Łä¸į

-0.15

 Ð²Ð¾Ð¾Ð±ÑīÐµ

-0.14

Sometimes

-0.14

POSITIVE LOGITS

 likely

0.84

 probably

0.80

 most

0.74

likely

0.73

probably

0.70

 Likely

0.66

 Probably

0.65

Probably

0.63

 probable

0.59

most

0.57

Activations Density 0.509%

phrases that indicate likelihood or probability regarding future events

No Comments

No Known Activations