INDEX

Explanations

data references in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

yet

-0.16

ilyn

-0.15

 recent

-0.14

 early

-0.14

seg

-0.14

 report

-0.13

yo

-0.13

 other

-0.13

 Boyd

-0.13

ein

-0.13

POSITIVE LOGITS

 RESULTS

0.19

RESULTS

0.18

ellar

0.16

Ø§Ø±Ú©

0.15

 eligible

0.15

ãģ¾ãģļ

0.15

onymous

0.15

ì´Ŀ

0.15

.DATA

0.15

.SP

0.14

Activations Density 0.073%

data references in a scientific context

No Comments

No Known Activations