INDEX

Explanations

references to the truth or beliefs about various topics

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ë´ī

-0.15

ManagerInterface

-0.14

Aspect

-0.14

loh

-0.14

isible

-0.14

zes

-0.14

 possibility

-0.13

ber

-0.13

 mentioned

-0.13

 mentions

-0.13

POSITIVE LOGITS

 meaning

0.31

 exact

0.25

 answer

0.23

 difference

0.21

 exactly

0.21

meaning

0.21

 nature

0.20

 precise

0.20

 identity

0.20

 proper

0.19

Activations Density 0.179%

references to the truth or beliefs about various topics

No Known Activations