INDEX

Explanations

references to reading articles or accessing further information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

baz

-0.15

ade

-0.15

itz

-0.15

 Gupta

-0.15

hus

-0.14

è³Ģ

-0.14

kn

-0.14

bast

-0.14

Î¶ÏĮ

-0.14

Ä

-0.13

POSITIVE LOGITS

ubar

0.15

ramid

0.15

å³°

0.15

dech

0.15

:"-

0.15

berra

0.15

asca

0.15

ãģ¡ãģ¯

0.15

ÙĨØ¬

0.14

.Automation

0.14

Activations Density 0.051%

references to reading articles or accessing further information

No Comments

No Known Activations