INDEX

Explanations

categories and labels related to content organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ÏĦÎµÏħ

-0.15

 ÙħØ±Ø§Øª

-0.15

é»İ

-0.14

lava

-0.14

åĿĬ

-0.14

.newBuilder

-0.14

ugin

-0.14

å¹¸

-0.14

RAR

-0.14

auge

-0.14

POSITIVE LOGITS

 Archives

0.19

 archives

0.16

hid

0.15

orsche

0.15

Wat

0.14

agnost

0.14

RIES

0.14

sud

0.14

ador

0.14

Activations Density 0.007%

categories and labels related to content organization

No Comments

No Known Activations