INDEX

Explanations

references to authors and their works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

avras

-0.17

ered

-0.16

ÙĩÙĪØ±

-0.15

uae

-0.14

ç«ĭãģ¦

-0.14

Lem

-0.14

atron

-0.14

Unsigned

-0.14

aved

-0.14

ductor

-0.14

POSITIVE LOGITS

phies

0.16

okt

0.16

mag

0.15

yles

0.15

ardu

0.15

toy

0.15

du

0.15

brig

0.14

ret

0.14

 cast

0.14

Activations Density 0.028%

references to authors and their works

No Comments

No Known Activations