INDEX

Explanations

references to sections and theorems in a mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

akit

-0.17

.metro

-0.15

richt

-0.15

byn

-0.14

``(

-0.13

([(

-0.13

olo

-0.13

lass

-0.13

 Bolt

-0.13

_SHADOW

-0.13

POSITIVE LOGITS

0.25

-\

0.20

 LABEL

0.20

 cref

0.20

\@

0.17

 Demir

0.17

(\

0.16

oref

0.16

 labeled

0.15

Activations Density 0.046%

references to sections and theorems in a mathematical context

No Comments

No Known Activations