INDEX

Explanations

terms related to fees, costs, and how they are accounted or assessed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

çĶ¨äºİ

-0.17

 ÑĩÑĤÐ¾Ð±Ñĭ

-0.15

tering

-0.15

ListOf

-0.15

para

-0.15

Ã³z

-0.15

pra

-0.15

ìĿ´ìĸ´

-0.14

 destin

-0.14

POSITIVE LOGITS

for

0.26

-for

0.23

 Ð·Ð°

0.20

_for

0.17

for

0.16

for

0.16

aska

0.16

ÙĪØ§

0.15

 ÙĦÙĦØŃ

0.15

.azure

0.15

Activations Density 0.154%

terms related to fees, costs, and how they are accounted or assessed

No Comments

No Known Activations