INDEX

Explanations

references to configuration settings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

croft

-0.16

olas

-0.15

çĬ

-0.15

sak

-0.15

Ã±ana

-0.14

ãģĤãģ£ãģŁ

-0.14

ushima

-0.14

ÑĢÐ¾Ð²Ð¸Ñĩ

-0.14

sic

-0.14

erek

-0.14

POSITIVE LOGITS

uten

0.15

iÃ³

0.15

 Ð¾ÐºÑĢÑĥÐ¶

0.14

å¤ªéĥİ

0.14

emple

0.14

linkplain

0.14

.SwingConstants

0.14

zzo

0.14

aepernick

0.13

Ð¾ÐºÐ¾Ð½

0.13

Activations Density 0.016%

references to configuration settings

No Comments

No Known Activations