INDEX

Explanations

references to differences or variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ertest

-0.15

gres

-0.15

.micro

-0.15

uchen

-0.15

omi

-0.15

 undermin

-0.14

/mol

-0.14

 trÃ¬

-0.14

fal

-0.14

ÐµÑĢÐ¶Ð°Ð²

-0.14

POSITIVE LOGITS

 than

0.23

 THAN

0.19

than

0.18

-than

0.17

iator

0.17

iators

0.17

 different

0.16

 altogether

0.16

_than

0.16

 Ã¤n

0.16

Activations Density 0.251%

references to differences or variations in various contexts

No Comments

No Known Activations

references to differences or variations in various contexts

No Comments

No Known Activations