INDEX

Explanations

references to academic journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

agit

-0.16

fall

-0.16

eless

-0.16

elyn

-0.16

ater

-0.15

ertools

-0.15

ÏĩÎµÎ¹

-0.14

esso

-0.14

ulti

-0.14

éĤ£éĩĮ

-0.14

POSITIVE LOGITS

istic

0.22

ize

0.20

isted

0.19

ized

0.19

izes

0.19

ists

0.17

ised

0.17

istics

0.16

ysis

0.16

ista

0.16

Activations Density 0.023%

references to academic journals and publications

No Comments

No Known Activations