INDEX

Explanations

sequences and relationships between tasks, concepts, and evaluations of conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 youngest

-0.16

 Pocket

-0.16

 pocket

-0.15

Pocket

-0.15

unger

-0.15

urga

-0.15

 Retirement

-0.14

 Harry

-0.14

opot

-0.14

 retirement

-0.14

POSITIVE LOGITS

 intermediate

0.27

 Intermediate

0.25

Intermediate

0.23

 intermediary

0.22

 middle

0.21

middle

0.20

.middle

0.20

ãĢģä¸Ń

0.19

 medium

0.19

 orta

0.19

Activations Density 0.178%

sequences and relationships between tasks, concepts, and evaluations of conditions

No Comments

No Known Activations