INDEX

Explanations

technical terms related to data processing and software features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Ø¯Ø§Ø¯

-0.15

leys

-0.15

 Budd

-0.15

andel

-0.15

uki

-0.14

 Ð·Ð°ÐºÐ¾Ð½Ð¾Ð¼

-0.14

.nano

-0.14

untu

-0.14

ajs

-0.14

POSITIVE LOGITS

ut

0.20

 caric

0.19

 scar

0.17

riel

0.17

 predis

0.16

scar

0.16

tel

0.15

çķª

0.15

 gest

0.15

Ïİ

0.15

Activations Density 0.020%

technical terms related to data processing and software features

No Comments

No Known Activations