INDEX

Explanations

instances of the word "in" and related phrases indicating inclusion or reference

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

gui

-0.15

ç¢

-0.15

igkeit

-0.14

æ³°

-0.14

Jeg

-0.14

rite

-0.14

Eag

-0.14

 NavParams

-0.14

Ð¾Ð³Ñĥ

-0.14

 ØŃÙģ

-0.14

POSITIVE LOGITS

undra

0.19

ãĤ¹ãĤ¯

0.15

arti

0.15

strup

0.15

halt

0.14

 Convers

0.14

ioni

0.14

embro

0.14

celik

0.13

flater

0.13

Activations Density 0.110%

instances of the word "in" and related phrases indicating inclusion or reference

No Comments

No Known Activations