INDEX

Explanations

the name "Berg" in various contexts throughout the document

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

eru

-0.14

andle

-0.14

udd

-0.14

 flips

-0.14

osity

-0.13

ISION

-0.13

odi

-0.13

aversable

-0.13

UMP

-0.13

nels

-0.13

POSITIVE LOGITS

0.17

arness

0.16

æĭ³

0.16

heimer

0.16

ATAB

0.15

ÐļÐ¢

0.15

ersen

0.15

UNET

0.14

 Ting

0.14

ÏĢÎµÎ¹

0.14

Activations Density 0.009%

the name "Berg" in various contexts throughout the document

No Comments

No Known Activations