INDEX

Explanations

references to figures, tables, and theorems in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

avo

-0.14

.InnerException

-0.14

velt

-0.13

akit

-0.13

.HttpContext

-0.13

 à¤«à¤°

-0.13

 Voor

-0.13

ÐĤ

-0.13

spr

-0.12

POSITIVE LOGITS

 cref

0.16

è£ķ

0.15

ãĥĥãĤ·ãĥ¥

0.15

 Listings

0.14

.scalablytyped

0.14

 è£

0.14

oins

0.14

UniqueId

0.14

icho

0.14

infeld

0.14

Activations Density 0.054%

references to figures, tables, and theorems in the text

No Comments

No Known Activations